default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDPhilip Torr 0001
Philip H. S. Torr – Philip Hilaire Sean Torr
Person information
- affiliation: University of Oxford, Department of Engineering Science, Oxford, UK
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
[i365]Fazl Barez, Tingchen Fu, Ameya Prabhu, Stephen Casper, Amartya Sanyal, Adel Bibi, Aidan O'Gara, Robert Kirk, Ben Bucknall, Tim Fist, Luke Ong, Philip Torr, Kwok-Yan Lam, Robert Trager, David Krueger, Sören Mindermann, José Hernández-Orallo, Mor Geva, Yarin Gal:
Open Problems in Machine Unlearning for AI Safety. CoRR abs/2501.04952 (2025)- [i364]Kumail Alhamoud, Shaden Alshammari, Yonglong Tian, Guohao Li, Philip Torr, Yoon Kim, Marzyeh Ghassemi:
Vision-Language Models Do Not Understand Negation. CoRR abs/2501.09425 (2025) - [i363]Aleksandar Petrov, Shruti Agarwal, Philip H. S. Torr, Adel Bibi, John P. Collomosse:
On the Coexistence and Ensembling of Watermarks. CoRR abs/2501.17356 (2025) - [i362]Georgia Channing, Aqib Mahfuz, Mark van der Wilk, Philip Torr, Fabio Pizzati, Christian Schröder de Witt:
PSyDUCK: Training-Free Steganography for Latent Diffusion. CoRR abs/2501.19172 (2025) - [i361]Kalyan Ramakrishnan, Lars L. Schaaf, Chen Lin, Guangrun Wang, Philip Torr:
Implicit Neural Representations for Chemical Reaction Paths. CoRR abs/2502.15843 (2025) - [i360]Cornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Kayser, Tom Rainforth, Thomas Lukasiewicz, Bernard Ghanem, Philip H. S. Torr, Adel Bibi:
Shh, don't say that! Domain Certification in LLMs. CoRR abs/2502.19320 (2025) - [i359]Lovis Heindrich, Philip Torr, Fazl Barez, Veronika Thost:
Do Sparse Autoencoders Generalize? A Case Study of Answerability. CoRR abs/2502.19964 (2025) - [i358]Magnus Sesodia, Alina Petrova, John Armour, Thomas Lukasiewicz, Oana-Maria Camburu, Puneet K. Dokania, Philip Torr, Christian Schröder de Witt:
AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction. CoRR abs/2503.00128 (2025) - [i357]Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr:
Mixture of Experts Made Intrinsically Interpretable. CoRR abs/2503.07639 (2025) - [i356]Lukas Aichberger, Alasdair Paren, Yarin Gal, Philip Torr, Adel Bibi:
Attacking Multimodal OS Agents with Malicious Image Patches. CoRR abs/2503.10809 (2025) - [i355]Jensen Zhou, Hang Gao, Vikram Voleti, Aaryaman Vasishta, Chun-Han Yao, Mark Boss, Philip Torr, Christian Rupprecht, Varun Jampani:
Stable Virtual Camera: Generative View Synthesis with Diffusion Models. CoRR abs/2503.14489 (2025) - 2024
- [j97]Yudong Luo, Yangchen Pan, Han Wang, Philip Torr, Pascal Poupart:
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization. RLJ 2: 573-592 (2024) - [j96]Chenyi Jiang, Yuming Shen, Dubing Chen, Haofeng Zhang
, Ling Shao, Philip H. S. Torr:
Estimation of Near-Instance-Level Attribute Bottleneck for Zero-Shot Learning. Int. J. Comput. Vis. 132(8): 2962-2988 (2024) - [j95]Li Zhang, Jiachen Lu, Sixiao Zheng, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng, Philip H. S. Torr:
Vision Transformers: From Semantic Segmentation to Dense Prediction. Int. J. Comput. Vis. 132(12): 6142-6162 (2024) - [j94]Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar:
Scaling the Convex Barrier with Sparse Dual Algorithms. J. Mach. Learn. Res. 25: 61:1-61:51 (2024) - [j93]Ehsan Imani, Guojun Zhang, Runjia Li, Jun Luo, Pascal Poupart, Philip H. S. Torr, Yangchen Pan:
Label Alignment Regularization for Distribution Shift. J. Mach. Learn. Res. 25: 247:1-247:32 (2024) - [j92]Jiaming Zhang, Kailun Yang, Hao Shi, Simon Reiß, Kunyu Peng, Chaoxiang Ma, Haodong Fu, Philip H. S. Torr, Kaiwei Wang, Rainer Stiefelhagen:
Behind Every Domain There is a Shift: Adapting Distortion-Aware Vision Transformers for Panoramic Semantic Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 46(12): 8549-8567 (2024) - [j91]Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqian Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip Torr:
A Survey on Transferability of Adversarial Examples Across Deep Neural Networks. Trans. Mach. Learn. Res. 2024 (2024) - [j90]Jishnu Mukhoti, Yarin Gal, Philip Torr, Puneet K. Dokania:
Fine-tuning can cripple your foundation model; preserving features may be the solution. Trans. Mach. Learn. Res. 2024 (2024) - [j89]Bin Ren, Hao Tang, Fanyang Meng, Runwei Ding, Philip Torr, Nicu Sebe:
Cloth Interactive Transformer for Virtual Try-On. ACM Trans. Multim. Comput. Commun. Appl. 20(4): 92:1-92:20 (2024) - [c375]Linsheng Chen, Guangrun Wang, Liuchun Yuan, Keze Wang, Ken Deng, Philip H. S. Torr:
NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning. AAAI 2024: 1156-1164 - [c374]Tim Franzmeyer, Aleksandar Shtedritski, Samuel Albanie, Philip Torr, João F. Henriques, Jakob N. Foerster:
HelloFresh: LLM Evalutions on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits. ACL (Findings) 2024: 12702-12716 - [c373]Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim, Bernard Ghanem, Philip Torr, Adel Bibi:
From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web. CoLLAs 2024: 534-559 - [c372]Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu:
Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation. CVPR 2024: 12006-12016 - [c371]Shuyang Sun, Runjia Li, Philip Torr, Xiuye Gu, Siyang Li:
CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor. CVPR 2024: 13171-13182 - [c370]Yufan Chen, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ruiping Liu, Philip Torr, Rainer Stiefelhagen:
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models. CVPR 2024: 15556-15566 - [c369]Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati, Philip H. S. Torr, Adel Bibi, Bernard Ghanem:
On Pretraining Data Diversity for Self-Supervised Learning. ECCV (56) 2024: 54-71 - [c368]Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian D. Reid, Philip Torr, Victor Adrian Prisacariu:
GaussCtrl: Multi-view Consistent Text-Driven 3D Gaussian Splatting Editing. ECCV (14) 2024: 55-71 - [c367]Avery Ma, Amir-massoud Farahmand, Yangchen Pan, Philip Torr, Jindong Gu:
Improving Adversarial Transferability via Model Alignment. ECCV (62) 2024: 74-92 - [c366]Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati:
Latent Guard: A Safety Framework for Text-to-Image Generation. ECCV (26) 2024: 93-109 - [c365]Zijian He, Peixin Chen, Guangrun Wang, Guanbin Li, Philip H. S. Torr, Liang Lin:
WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models. ECCV (17) 2024: 123-139 - [c364]Qilang Ye, Zitong Yu, Rui Shao, Xinyu Xie, Philip Torr, Xiaochun Cao:
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios. ECCV (10) 2024: 146-164 - [c363]Yixuan Wu, Yizhou Wang, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Philip Torr, Jian Wu:
DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM. ECCV (32) 2024: 164-182 - [c362]Fengyuan Liu, Haochen Luo, Yiming Li, Philip Torr, Jindong Gu:
Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution. ECCV (62) 2024: 282-301 - [c361]Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht:
Scene-Conditional 3D Object Stylization and Composition. ECCV (68) 2024: 289-305 - [c360]Junlin Han, Filippos Kokkinos, Philip Torr:
VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models. ECCV (2) 2024: 333-350 - [c359]A. Tuan Nguyen, Kai Sheng Tai, Bor-Chun Chen, Satya Narayan Shukla, Hanchao Yu, Philip Torr, Tai-Peng Tian, Ser-Nam Lim:
uCAP: An Unsupervised Prompting Method for Vision-Language Models. ECCV (74) 2024: 425-439 - [c358]Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Grégory Rogez:
Placing Objects in Context via Inpainting for Out-of-Distribution Segmentation. ECCV (45) 2024: 456-473 - [c357]Michael Lan, Philip Torr, Fazl Barez:
Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models. EMNLP 2024: 12576-12601 - [c356]Hasan Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay:
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. EMNLP (Findings) 2024: 13033-13046 - [c355]Youssef Mohamed, Runjia Li, Ibrahim Said Ahmad, Kilichbek Haydarov, Philip Torr, Kenneth Church, Mohamed Elhoseiny:
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages. EMNLP 2024: 20939-20962 - [c354]Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip Torr:
Porf: Pose residual field for accurate Neural surface Reconstruction. ICLR 2024 - [c353]Tim Franzmeyer, Edith Elkind, Philip Torr, Jakob Nicolaus Foerster, João F. Henriques:
Select to Perfect: Imitating desired behavior from large multi-agent data. ICLR 2024 - [c352]Tim Franzmeyer, Stephen Marcus McAleer, João F. Henriques, Jakob Nicolaus Foerster, Philip Torr, Adel Bibi, Christian Schröder de Witt:
Illusory Attacks: Information-theoretic detectability matters in adversarial attacks. ICLR 2024 - [c351]Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu:
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images. ICLR 2024 - [c350]Haoheng Lan, Jindong Gu, Philip Torr, Hengshuang Zhao:
Influencer Backdoor Attack on Semantic Segmentation. ICLR 2024 - [c349]Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr:
An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models. ICLR 2024 - [c348]Aleksandar Petrov, Philip Torr, Adel Bibi:
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations. ICLR 2024 - [c347]Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr, Bo Zhao:
Real-Fake: Effective Training Data Synthesis Through Distribution Matching. ICLR 2024 - [c346]Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip Torr, Adel Bibi, Mohamed Elhoseiny:
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation. ICLR 2024 - [c345]Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy Dj Dvijotham, Philip Torr, M. Pawan Kumar:
Efficient Error Certification for Physics-Informed Neural Networks. ICML 2024 - [c344]Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan A. Nolazco-Flores, Lori Landay, Matthew Thomas Jackson, Paul Röttger, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster:
Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI. ICML 2024 - [c343]Aleksandar Petrov, Philip Torr, Adel Bibi:
Prompting a Pretrained Transformer Can Be a Universal Approximator. ICML 2024 - [c342]Francesco Pinto, Nathalie Rauschmayr, Florian Tramèr, Philip Torr, Federico Tombari:
Extracting Training Data From Document-Based VQA Models. ICML 2024 - [c341]Yibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Adel Bibi, Philip Torr, Bernard Ghanem:
Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation. ICML 2024 - [c340]Jianhao Yuan, Francesco Pinto, Adam Davies, Philip Torr:
Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators. ICML 2024 - [c339]Kumail Alhamoud, Yasir Ghunaim, Motasem Alfarra, Thomas Hartvigsen, Philip Torr, Bernard Ghanem, Adel Bibi, Marzyeh Ghassemi:
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging. MICCAI (10) 2024: 383-393 - [c338]Bruno Andreis, Bedionita Soro, Philip H. S. Torr, Sung Ju Hwang:
Set-based Neural Network Encoding Without Weight Tying. NeurIPS 2024 - [c337]Botos Csaba, Wenxuan Zhang, Matthias Müller, Ser Nam Lim, Philip Torr, Adel Bibi:
Label Delay in Online Continual Learning. NeurIPS 2024 - [c336]Arshia Hemmat, Adam Davies, Tom A. Lamb, Jianhao Yuan, Philip Torr, Ashkan Khakzar, Francesco Pinto:
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models. NeurIPS 2024 - [c335]Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip Torr, Amartya Sanyal, Puneet K. Dokania:
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study. NeurIPS 2024 - [c334]Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez:
Interpreting Learned Feedback Patterns in Large Language Models. NeurIPS 2024 - [c333]Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip Torr, Lewis Hammond, Christian Schröder de Witt:
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography. NeurIPS 2024 - [c332]Aleksandar Petrov, Tom A. Lamb, Alasdair Paren, Philip Torr, Adel Bibi:
Universal In-Context Approximation By Prompting Fully Recurrent Models. NeurIPS 2024 - [c331]Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip Torr, Ozan Sener, Puneet K. Dokania:
RanDumb: Random Representations Outperform Online Continually Learned Representations. NeurIPS 2024 - [c330]Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie:
Efficient Lifelong Model Evaluation in an Era of Rapid Progress. NeurIPS 2024 - [c329]Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip Torr, Adel Bibi, Samuel Albanie, Matthias Bethge:
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance. NeurIPS 2024 - [c328]Shuang Wu, Youtian Lin, Yifei Zeng, Feihu Zhang, Jingxi Xu, Philip Torr, Xun Cao, Yao Yao:
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer. NeurIPS 2024 - [c327]Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Shiyang Lai, Kai Shu, Jindong Gu, Adel Bibi, Ziniu Hu, David Jurgens, James Evans, Philip Torr, Bernard Ghanem, Guohao Li:
Can Large Language Model Agents Simulate Human Trust Behavior? NeurIPS 2024 - [i354]Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu:
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images. CoRR abs/2401.11170 (2024) - [i353]Hasan Abed Al Kader Hammoud, Hani Itani, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem:
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training? CoRR abs/2402.01832 (2024) - [i352]Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Kai Shu, Adel Bibi, Ziniu Hu, Philip Torr, Bernard Ghanem, Guohao Li:
Can Large Language Model Agents Simulate Human Trust Behaviors? CoRR abs/2402.04559 (2024) - [i351]Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H. S. Torr, Lewis Hammond, Christian Schröder de Witt:
Secret Collusion Among Generative AI Agents. CoRR abs/2402.07510 (2024) - [i350]Chen Lin, Liheng Ma, Yiyang Chen, Wanli Ouyang, Michael M. Bronstein, Philip H. S. Torr:
Revealing Decurve Flows for Generalized Graph Propagation. CoRR abs/2402.08480 (2024) - [i349]Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H. S. Torr, Ozan Sener, Puneet K. Dokania:
RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning. CoRR abs/2402.08823 (2024) - [i348]Gengyuan Hu, Gengchen Wei, Zekun Lou, Philip H. S. Torr, Wanli Ouyang, Hansen Zhong, Chen Lin:
Self-consistent Validation for Machine Learning Electronic Structure. CoRR abs/2402.10186 (2024) - [i347]Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal:
Corrective Machine Unlearning. CoRR abs/2402.14015 (2024) - [i346]Aleksandar Petrov, Philip H. S. Torr, Adel Bibi:
Prompting a Pretrained Transformer Can Be a Universal Approximator. CoRR abs/2402.14753 (2024) - [i345]Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu:
Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images. CoRR abs/2402.14899 (2024) - [i344]Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Grégory Rogez:
Placing Objects in Context via Inpainting for Out-of-distribution Segmentation. CoRR abs/2402.16392 (2024) - [i343]Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie:
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress. CoRR abs/2402.19472 (2024) - [i342]Linsheng Chen, Guangrun Wang, Liuchun Yuan, Keze Wang, Ken Deng, Philip H. S. Torr:
NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning. CoRR abs/2403.01325 (2024) - [i341]Qilang Ye, Zitong Yu, Rui Shao, Xinyu Xie, Philip Torr, Xiaochun Cao:
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios. CoRR abs/2403.04640 (2024) - [i340]Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian D. Reid, Philip Torr, Victor Adrian Prisacariu:
GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing. CoRR abs/2403.08733 (2024) - [i339]Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr:
An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models. CoRR abs/2403.09766 (2024) - [i338]Yudong Luo, Yangchen Pan, Han Wang, Philip Torr, Pascal Poupart:
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization. CoRR abs/2403.11062 (2024) - [i337]Junlin Han, Filippos Kokkinos, Philip Torr:
VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models. CoRR abs/2403.12034 (2024) - [i336]Yixuan Wu, Yizhou Wang, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Jian Wu, Philip Torr:
DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM. CoRR abs/2403.12488 (2024) - [i335]Anjun Hu, Jindong Gu, Francesco Pinto, Konstantinos Kamnitsas, Philip Torr:
As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks? CoRR abs/2403.12693 (2024) - [i334]Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem:
On Pretraining Data Diversity for Self-Supervised Learning. CoRR abs/2403.13808 (2024) - [i333]Yufan Chen, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ruiping Liu, Philip Torr, Rainer Stiefelhagen:
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models. CoRR abs/2403.14442 (2024) - [i332]Yuanze Lin, Ronald Clark, Philip Torr:
DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion. CoRR abs/2403.17237 (2024) - [i331]Fengyuan Liu, Haochen Luo, Yiming Li, Philip Torr, Jindong Gu:
Model-agnostic Origin Attribution of Generated Images with Few-shot Examples. CoRR abs/2404.02697 (2024) - [i330]Shuo Chen, Zhen Han, Bailan He, Zifeng Ding, Wenqian Yu, Philip Torr, Volker Tresp, Jindong Gu:
Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks? CoRR abs/2404.03411 (2024) - [i329]Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip H. S. Torr, Adel Bibi, Samuel Albanie, Matthias Bethge:
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance. CoRR abs/2404.04125 (2024) - [i328]Yuanfeng Xu, Yuhao Chen, Zhongzhan Huang, Zijian He, Guangrun Wang, Philip Torr, Liang Lin:
AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment. CoRR abs/2404.04946 (2024) - [i327]Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati:
Latent Guard: a Safety Framework for Text-to-image Generation. CoRR abs/2404.08031 (2024) - [i326]Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, Philip Torr:
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies. CoRR abs/2404.09447 (2024) - [i325]Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip H. S. Torr, Adel Bibi, Mohamed Elhoseiny:
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation. CoRR abs/2404.12766 (2024) - [i324]Yangchen Pan, Junfeng Wen, Chenjun Xiao, Philip Torr:
An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models. CoRR abs/2404.15518 (2024) - [i323]Kuofeng Gao, Jindong Gu, Yang Bai, Shu-Tao Xia, Philip Torr, Wei Liu, Zhifeng Li:
Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples. CoRR abs/2404.16557 (2024) - [i322]Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan A. Nolazco-Flores, Lori Landay, Matthew Thomas Jackson, Paul Röttger, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster:
Near to Mid-term Risks and Opportunities of Open Source Generative AI. CoRR abs/2404.17047 (2024) - [i321]Tim Franzmeyer, Edith Elkind, Philip Torr, Jakob N. Foerster, João F. Henriques:
Select to Perfect: Imitating desired behavior from large multi-agent data. CoRR abs/2405.03735 (2024) - [i320]Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Aaron Purewal, Botos Csaba, Fabro Steibel, Fazel Keshtkar, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan Arturo Nolazco, Lori Landay, Matthew Thomas Jackson, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster:
Risks and Opportunities of Open-Source Generative AI. CoRR abs/2405.08597 (2024) - [i319]Xianzheng Ma, Yash Bhalgat, Brandon Smart, Shuai Chen, Xinghui Li, Jian Ding, Jindong Gu, Dave Zhenyu Chen, Songyou Peng, Jia-Wang Bian, Philip H. S. Torr, Marc Pollefeys, Matthias Nießner, Ian D. Reid, Angel X. Chang, Iro Laina, Victor Adrian Prisacariu:
When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models. CoRR abs/2405.10255 (2024) - [i318]Cornelius Emde, Francesco Pinto, Thomas Lukasiewicz, Philip H. S. Torr, Adel Bibi:
Towards Certification of Uncertainty Calibration under Adversarial Attacks. CoRR abs/2405.13922 (2024) - [i317]Shuang Wu, Youtian Lin, Feihu Zhang, Yifei Zeng, Jingxi Xu, Philip Torr, Xun Cao, Yao Yao:
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer. CoRR abs/2405.14832 (2024) - [i316]Aleksandar Petrov, Tom A. Lamb, Alasdair Paren, Philip Torr, Adel Bibi:
Universal In-Context Approximation By Prompting Fully Recurrent Models. CoRR abs/2406.01424 (2024) - [i315]Razieh Rezaei, Masoud Jalili Sabet, Jindong Gu, Daniel Rueckert, Philip Torr, Ashkan Khakzar:
Learning Visual Prompts for Guiding the Attention of Vision Transformers. CoRR abs/2406.03303 (2024) - [i314]Tim Franzmeyer, Aleksandar Shtedritski, Samuel Albanie, Philip Torr, João F. Henriques, Jakob N. Foerster:
HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits. CoRR abs/2406.03428 (2024) - [i313]Yibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Hammoud, Adel Bibi, Philip Torr, Bernard Ghanem:
Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation. CoRR abs/2406.05222 (2024) - [i312]Gengyuan Zhang, Mang Ling Ada Fok, Yan Xia, Yansong Tang, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu:
Localizing Events in Videos with Multimodal Queries. CoRR abs/2406.10079 (2024) - [i311]Francisco Eiras, Aleksandar Petrov, Philip H. S. Torr, M. Pawan Kumar, Adel Bibi:
Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models. CoRR abs/2406.10288 (2024) - [i310]Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay:
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. CoRR abs/2406.14563 (2024) - [i309]Henghui Ding, Chang Liu, Yunchao Wei, Nikhila Ravi, Shuting He, Song Bai, Philip Torr, Deshui Miao, Xin Li, Zhenyu He, Yaowei Wang, Ming-Hsuan Yang, Zhensong Xu, Jiangtao Yao, Chengjing Wu, Ting Liu, Luoqi Liu, Xinyu Liu, Jing Zhang, Kexin Zhang, Yuting Yang, Licheng Jiao, Shuyuan Yang, Mingqi Gao, Jingnan Luo, Jinyu Yang, Jungong Han, Feng Zheng, Bin Cao, Yisi Zhang, Xuanxu Lin, Xingjian He, Bo Zhao, Jing Liu, Feiyu Pan, Hao Fang, Xiankai Lu:
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results. CoRR abs/2406.17005 (2024) - [i308]Tianqi Xu, Linyao Chen, Dai-Jie Wu, Yanjun Chen, Zecheng Zhang, Xiang Yao, Zhiqiang Xie, Yongchao Chen, Shilong Liu, Bochen Qian, Philip Torr, Bernard Ghanem, Guohao Li:
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. CoRR abs/2407.01511 (2024) - [i307]Yuanze Lin, Yunsheng Li, Dongdong Chen, Weijian Xu, Ronald Clark, Philip Torr, Lu Yuan:
Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge. CoRR abs/2407.04681 (2024) - [i306]Francesco Pinto, Nathalie Rauschmayr, Florian Tramèr, Philip Torr, Federico Tombari:
Extracting Training Data from Document-Based VQA Models. CoRR abs/2407.08707 (2024) - [i305]Kumail Alhamoud, Yasir Ghunaim, Motasem Alfarra, Thomas Hartvigsen, Philip Torr, Bernard Ghanem, Adel Bibi, Marzyeh Ghassemi:
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging. CoRR abs/2407.08822 (2024) - [i304]Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania:
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study. CoRR abs/2407.10264 (2024) - [i303]Zijian He, Peixin Chen, Guangrun Wang, Guanbin Li, Philip H. S. Torr, Liang Lin:
WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models. CoRR abs/2407.10625 (2024) - [i302]Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen, Shiyang Lai, Xiongxiao Xu, Jia-Chen Gu, Jindong Gu, Huaxiu Yao, Chaowei Xiao, Xifeng Yan, William Yang Wang, Philip Torr, Dawn Song, Kai Shu:
Can Editing LLMs Inject Harm? CoRR abs/2407.20224 (2024) - [i301]Ekaterina Iakovleva, Fabio Pizzati, Philip Torr, Stéphane Lathuilière:
Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing. CoRR abs/2407.20232 (2024) - [i300]Zeyu Yang, Nan Song, Wei Li, Xiatian Zhu, Li Zhang, Philip H. S. Torr:
DeepInteraction++: Multi-Modality Interaction for Autonomous Driving. CoRR abs/2408.05075 (2024) - [i299]Wenxuan Zhang, Philip H. S. Torr, Mohamed Elhoseiny, Adel Bibi:
Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models. CoRR abs/2408.15313 (2024) - [i298]Runjia Li, Junlin Han, Luke Melas-Kyriazi, Chunyi Sun, Zhaochong An, Zhongrui Gui, Shuyang Sun, Philip Torr, Tomas Jakab:
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer. CoRR abs/2409.08271 (2024) - [i297]Tong Liu, Zhixin Lai, Gengyuan Zhang, Philip Torr, Vera Demberg, Volker Tresp, Jindong Gu:
Multimodal Pragmatic Jailbreak on Text-to-image Models. CoRR abs/2409.19149 (2024) - [i296]Junlin Han, Jianyuan Wang, Andrea Vedaldi, Philip Torr, Filippos Kokkinos:
Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation. CoRR abs/2410.00890 (2024) - [i295]Haokun Chen, Hang Li, Yao Zhang, Gengyuan Zhang, Jinhe Bi, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp:
FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models. CoRR abs/2410.04810 (2024) - [i294]Michael Lan, Philip Torr, Austin Meek, Ashkan Khakzar, David Krueger, Fazl Barez:
Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models. CoRR abs/2410.06981 (2024) - [i293]Clement Neo, Luke Ong, Philip Torr, Mor Geva, David Krueger, Fazl Barez:
Towards Interpreting Visual Information Processing in Vision-Language Models. CoRR abs/2410.07149 (2024) - [i292]Georgia Channing, Juil Sock, Ronald Clark, Philip Torr, Christian Schröder de Witt:
Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap. CoRR abs/2410.07436 (2024) - [i291]Constantin Venhoff, Anisoara Calinescu, Philip Torr, Christian Schröder de Witt:
SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders. CoRR abs/2410.07456 (2024) - [i290]Tingchen Fu, Mrinank Sharma, Philip Torr, Shay B. Cohen, David Krueger, Fazl Barez:
PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning. CoRR abs/2410.08811 (2024) - [i289]Ling Yang, Zixiang Zhang, Junlin Han, Bohan Zeng, Runjia Li, Philip Torr, Wentao Zhang:
Semantic Score Distillation Sampling for Compositional Text-to-3D Generation. CoRR abs/2410.09009 (2024) - [i288]Qianyi Deng, Oishi Deb, Amir Patel, Christian Rupprecht, Philip Torr, Niki Trigoni, Andrew Markham:
Towards Multi-Modal Animal Pose Estimation: An In-Depth Analysis. CoRR abs/2410.09312 (2024) - [i287]Yu Lei, Hao Liu, Chengxing Xie, Songjia Liu, Zhiyu Yin, Canyu Chen, Guohao Li, Philip Torr, Zhen Wu:
FairMindSim: Alignment of Behavior, Emotion, and Belief in Humans and LLM Agents Amid Ethical Dilemmas. CoRR abs/2410.10398 (2024) - [i286]Samuele Marro, Emanuele La Malfa, Jesse Wright, Guohao Li, Nigel Shadbolt, Michael J. Wooldridge, Philip Torr:
A Scalable Communication Protocol for Networks of Large Language Models. CoRR abs/2410.11905 (2024) - [i285]Kumud Lakara, Juil Sock, Christian Rupprecht, Philip Torr, John P. Collomosse, Christian Schröder de Witt:
MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection. CoRR abs/2410.20140 (2024) - [i284]Tom A. Lamb, Adam Davies, Alasdair Paren, Philip H. S. Torr, Francesco Pinto:
Focus On This, Not That! Steering LLMs With Adaptive Feature Specification. CoRR abs/2410.22944 (2024) - [i283]Youssef Mohamed, Runjia Li, Ibrahim Said Ahmad, Kilichbek Haydarov, Philip Torr, Kenneth Ward Church, Mohamed Elhoseiny:
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages. CoRR abs/2411.03769 (2024) - [i282]Davide Buoso, Luke Robinson, Giuseppe Averta, Philip Torr, Tim Franzmeyer, Daniele De Martini:
Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval. CoRR abs/2411.04006 (2024) - [i281]Arshia Hemmat, Adam Davies, Tom A. Lamb, Jianhao Yuan, Philip Torr, Ashkan Khakzar, Francesco Pinto:
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models. CoRR abs/2411.06287 (2024) - [i280]Ziyi Yang, Zaibin Zhang, Zirui Zheng, Yuxian Jiang, Ziyue Gan, Zhiyu Wang, Zijian Ling, Jinsong Chen, Martz Ma, Bowen Dong, Prateek Gupta, Shuyue Hu, Zhenfei Yin, Guohao Li, Xu Jia, Lijun Wang, Bernard Ghanem, Huchuan Lu, Chaochao Lu, Wanli Ouyang, Yu Qiao, Philip Torr, Jing Shao:
OASIS: Open Agent Social Interaction Simulations with One Million Agents. CoRR abs/2411.11581 (2024) - [i279]Alejandro Pardo, Fabio Pizzati, Tong Zhang, Alexander Pondaven, Philip Torr, Juan Camilo Pérez, Bernard Ghanem:
MatchDiffusion: Training-free Generation of Match-cuts. CoRR abs/2411.18677 (2024) - [i278]Sumeet Ramesh Motwani, Chandler Smith, Rocktim Jyoti Das, Markian Rybchuk, Philip H. S. Torr, Ivan Laptev, Fabio Pizzati, Ronald Clark, Christian Schröder de Witt:
MALT: Improving Reasoning with Multi-Agent LLM Training. CoRR abs/2412.01928 (2024) - [i277]Yang Zhang, Er Jin, Yanfei Dong, Ashkan Khakzar, Philip Torr, Johannes Stegmaier, Kenji Kawaguchi:
Effortless Efficiency: Low-Cost Pruning of Diffusion Models. CoRR abs/2412.02852 (2024) - [i276]Kuofeng Gao, Shu-Tao Xia, Ke Xu, Philip Torr, Jindong Gu:
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models. CoRR abs/2412.05167 (2024) - [i275]Alexander Pondaven, Aliaksandr Siarohin, Sergey Tulyakov, Philip Torr, Fabio Pizzati:
Video Motion Transfer with Diffusion Transformers. CoRR abs/2412.07776 (2024) - [i274]Yuanze Lin, Yunsheng Li, Dongdong Chen, Weijian Xu, Ronald Clark, Philip H. S. Torr:
Olympus: A Universal Task Router for Computer Vision Tasks. CoRR abs/2412.09612 (2024) - [i273]Yunzhong Hou, Liang Zheng, Philip Torr:
Learning Camera Movement Control from Real-World Drone Videos. CoRR abs/2412.09620 (2024) - [i272]Hazel Kim, Adel Bibi, Philip Torr, Yarin Gal:
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Unanswerable Questions and Ambiguous Prompts. CoRR abs/2412.10246 (2024) - [i271]Runtao Liu, Chen I Chieh, Jindong Gu, Jipeng Zhang, Renjie Pi, Qifeng Chen, Philip Torr, Ashkan Khakzar, Fabio Pizzati:
SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation. CoRR abs/2412.10493 (2024) - [i270]Sarah Kiden, Bernd Stahl, Beverley Townsend, Carsten Maple, Charles Vincent, Fraser Sampson, Geoff Gilbert, Helen Smith, Jayati Deshmukh, Jen Ross, Jennifer Williams, Jesús Martínez del Rincón, Justyna Lisinska, Karen O'Shea, Márjory Da Costa-Abreu, Nelly Bencomo, Oishi Deb, Peter Winter, Phoebe Li, Philip Torr, Pin Lean Lau, Raquel Iniesta, Gopal Ramchurn, Sebastian Stein, Vahid Yazdanpanah:
Responsible AI Governance: A Response to UN Interim Report on Governing AI for Humanity. CoRR abs/2412.12108 (2024) - [i269]Zeyu Yang, Zijie Pan, Xiatian Zhu, Li Zhang, Yu-Gang Jiang, Philip H. S. Torr:
4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives. CoRR abs/2412.20720 (2024) - 2023
- [j88]Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe:
Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis. Int. J. Comput. Vis. 131(3): 644-658 (2023) - [j87]Ming-Ming Cheng, Peng-Tao Jiang, Linghao Han, Liang Wang, Philip H. S. Torr:
Deeply Explain CNN Via Hierarchical Decomposition. Int. J. Comput. Vis. 131(5): 1091-1105 (2023) - [j86]Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Yawen Cui, Jiehua Zhang, Philip H. S. Torr, Guoying Zhao:
PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer. Int. J. Comput. Vis. 131(6): 1307-1330 (2023) - [j85]Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe:
Local and Global GANs With Semantic-Aware Upsampling for Image Generation. IEEE Trans. Pattern Anal. Mach. Intell. 45(1): 768-784 (2023) - [j84]Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh:
Diagnosing and Preventing Instabilities in Recurrent Video Processing. IEEE Trans. Pattern Anal. Mach. Intell. 45(2): 1594-1605 (2023) - [j83]Weiming Hu, Qiang Wang, Li Zhang, Luca Bertinetto, Philip H. S. Torr:
SiamMask: A Framework for Fast Online Object Tracking and Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(3): 3072-3089 (2023) - [j82]Li Zhang, Mohan Chen, Anurag Arnab, Xiangyang Xue, Philip H. S. Torr:
Dynamic Graph Message Passing Networks. IEEE Trans. Pattern Anal. Mach. Intell. 45(5): 5712-5730 (2023) - [j81]Hao Tang, Philip H. S. Torr, Nicu Sebe:
Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation. IEEE Trans. Pattern Anal. Mach. Intell. 45(5): 6055-6071 (2023) - [j80]Song Bai, Philip H. S. Torr, Ranjay Krishna, Li Fei-Fei, Abhinav Gupta, Song-Chun Zhu:
Guest Editorial: Introduction to the Special Section on Graphs in Vision and Pattern Analysis. IEEE Trans. Pattern Anal. Mach. Intell. 45(6): 6867-6869 (2023) - [j79]Shanghua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip H. S. Torr:
Large-Scale Unsupervised Semantic Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(6): 7457-7476 (2023) - [j78]Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Philip H. S. Torr, Zhe Lin, Jiaya Jia:
Open World Entity Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(7): 8743-8756 (2023) - [j77]Shuyang Sun, Xiaoyu Yue, Hengshuang Zhao, Philip H. S. Torr, Song Bai:
Patch-Based Separable Transformer for Visual Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(7): 9241-9247 (2023) - [j76]Francesca Babiloni, Ioannis Marras, Jiankang Deng, Filippos Kokkinos, Matteo Maggioni, Grigorios Chrysos, Philip H. S. Torr, Stefanos Zafeiriou:
Linear Complexity Self-Attention With $3{\mathrm{rd}}$3 rd Order Polynomials. IEEE Trans. Pattern Anal. Mach. Intell. 45(11): 12726-12737 (2023) - [j75]Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr:
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(12): 14727-14744 (2023) - [j74]Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip Torr:
Catastrophic overfitting can be induced with discriminative non-robust features. Trans. Mach. Learn. Res. 2023 (2023) - [j73]Hao Tang, Hong Liu, Dan Xu, Philip H. S. Torr, Nicu Sebe:
AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks. IEEE Trans. Neural Networks Learn. Syst. 34(4): 1972-1987 (2023) - [c326]Dubing Chen, Yuming Shen, Haofeng Zhang, Philip H. S. Torr:
Deconstructed Generation-Based Zero-Shot Model. AAAI 2023: 295-303 - [c325]Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr:
Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation. AAAI 2023: 3222-3230 - [c324]Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
Sample-Dependent Adaptive Temperature Scaling for Improved Calibration. AAAI 2023: 14919-14926 - [c323]Jindong Gu, Fangyun Wei, Philip H. S. Torr, Han Hu:
Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks. BMVC 2023: 406-408 - [c322]Hasan Abed Al Kader Hammoud, Adel Bibi, Philip H. S. Torr, Bernard Ghanem:
Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs. CVPR Workshops 2023: 2338-2345 - [c321]Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi:
Computationally Budgeted Continual Learning: What Does Matter? CVPR 2023: 3698-3707 - [c320]Kejie Li, Jia-Wang Bian, Robert Castle, Philip H. S. Torr, Victor Adrian Prisacariu:
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices. CVPR 2023: 4892-4901 - [c319]Pau de Jorge, Riccardo Volpi, Philip H. S. Torr, Grégory Rogez:
Reliability in Semantic Segmentation: Are we on the Right Track? CVPR 2023: 7173-7182 - [c318]Yasir Ghunaim, Adel Bibi, Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H. S. Torr, Bernard Ghanem:
Real-Time Evaluation in Online Continual Learning: A New Hope. CVPR 2023: 11888-11897 - [c317]Jishnu Mukhoti, Tsung-Yu Lin, Omid Poursaeed, Rui Wang, Ashish Shah, Philip H. S. Torr, Ser-Nam Lim:
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning. CVPR 2023: 19413-19423 - [c316]A. Tuan Nguyen, Thanh Nguyen-Tang, Ser-Nam Lim, Philip H. S. Torr:
TIPI: Test Time Adaptation with Transformation Invariance. CVPR 2023: 24162-24171 - [c315]Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal:
Deep Deterministic Uncertainty: A New Simple Baseline. CVPR 2023: 24384-24394 - [c314]Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang:
Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer. ICCV 2023: 13899-13909 - [c313]Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H. S. Torr, Adel Bibi, Bernard Ghanem:
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? ICCV 2023: 18806-18815 - [c312]Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Philip H. S. Torr, Song Bai:
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes. ICCV 2023: 20167-20177 - [c311]Runjia Li, Shuyang Sun, Mohamed Elhoseiny, Philip H. S. Torr:
OxfordTVG-HIC: Can Machine Make Humorous Captions from Images? ICCV 2023: 20236-20246 - [c310]Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim:
Raising the Bar on the Evaluation of Out-of-Distribution Detection. ICCV (Workshops) 2023: 4367-4377 - [c309]Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip H. S. Torr, Song Bai, Xiaojuan Qi:
Is Synthetic Data from Generative Models Ready for Image Recognition? ICLR 2023 - [c308]Yuge Shi, Imant Daunhawer, Julia E. Vogt, Philip H. S. Torr, Amartya Sanyal:
How robust is unsupervised representation learning to distribution shift? ICLR 2023 - [c307]Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip H. S. Torr, Dacheng Tao:
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning. ICLR 2023 - [c306]Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim:
Graph Inductive Biases in Transformers without Message Passing. ICML 2023: 23321-23337 - [c305]Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi:
Certifying Ensembles: A General Certification Theory with S-Lipschitzness. ICML 2023: 27709-27736 - [c304]Yaoyuan Liang, Zhao Yang, Yansong Tang, Jiashuo Fan, Ziran Li, Jingang Wang, Philip H. S. Torr, Shao-Lun Huang:
LUNA: Language as Continuing Anchors for Referring Expression Comprehension. ACM Multimedia 2023: 5174-5184 - [c303]Shuo Chen, Jindong Gu, Zhen Han, Yunpu Ma, Philip H. S. Torr, Volker Tresp:
Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models. NeurIPS 2023 - [c302]Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr, Adel Bibi:
Language Model Tokenizers Introduce Unfairness Between Languages. NeurIPS 2023 - [c301]Shuyang Sun, Weijun Wang, Andrew G. Howard, Qihang Yu, Philip H. S. Torr, Liang-Chieh Chen:
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation. NeurIPS 2023 - [c300]Zifu Wang, Maxim Berman, Amal Rannen-Triki, Philip H. S. Torr, Devis Tuia, Tinne Tuytelaars, Luc Van Gool, Jiaqian Yu, Matthew B. Blaschko:
Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union. NeurIPS 2023 - [c299]Taras Rumezhak, Francisco Girbal Eiras, Philip H. S. Torr, Adel Bibi:
RANCER: Non-Axis Aligned Anisotropic Certification with Randomized Smoothing. WACV 2023: 4661-4669 - [i268]Yasir Ghunaim, Adel Bibi, Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H. S. Torr, Bernard Ghanem:
Real-Time Evaluation in Online Continual Learning: A New Paradigm. CoRR abs/2302.01047 (2023) - [i267]Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Philip H. S. Torr, Song Bai:
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes. CoRR abs/2302.01872 (2023) - [i266]Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip H. S. Torr, Dacheng Tao:
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning. CoRR abs/2302.03004 (2023) - [i265]Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Yawen Cui, Jiehua Zhang, Philip H. S. Torr, Guoying Zhao:
PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer. CoRR abs/2302.03548 (2023) - [i264]Kejie Li, Jia-Wang Bian, Robert Castle, Philip H. S. Torr, Victor Adrian Prisacariu:
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices. CoRR abs/2303.01932 (2023) - [i263]Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr:
Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation. CoRR abs/2303.06345 (2023) - [i262]Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet K. Dokania, Philip H. S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi:
Computationally Budgeted Continual Learning: What Does Matter? CoRR abs/2303.11165 (2023) - [i261]Pau de Jorge, Riccardo Volpi, Philip H. S. Torr, Grégory Rogez:
Reliability in Semantic Segmentation: Are We on the Right Track? CoRR abs/2303.11298 (2023) - [i260]Haoheng Lan, Jindong Gu, Philip H. S. Torr, Hengshuang Zhao:
Influencer Backdoor Attack on Semantic Segmentation. CoRR abs/2303.12054 (2023) - [i259]Hasan Abed Al Kader Hammoud, Adel Bibi, Philip H. S. Torr, Bernard Ghanem:
Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs. CoRR abs/2303.13211 (2023) - [i258]Jindong Gu, Ahmad Beirami, Xuezhi Wang, Alex Beutel, Philip H. S. Torr, Yao Qin:
Towards Robust Prompts on Vision-Language Models. CoRR abs/2304.08479 (2023) - [i257]Ondrej Bohdal, Timothy M. Hospedales, Philip H. S. Torr, Fazl Barez:
Fairness in AI and Its Long-Term Implications on Society. CoRR abs/2304.09826 (2023) - [i256]Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr, Adel Bibi:
Certifying Ensembles: A General Certification Theory with S-Lipschitzness. CoRR abs/2304.13019 (2023) - [i255]Ameya Prabhu, Zhipeng Cai, Puneet K. Dokania, Philip H. S. Torr, Vladlen Koltun, Ozan Sener:
Online Continual Learning Without the Storage Constraint. CoRR abs/2305.09253 (2023) - [i254]Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H. S. Torr, Adel Bibi, Bernard Ghanem:
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right? CoRR abs/2305.09275 (2023) - [i253]Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy (Dj) Dvijotham, Philip H. S. Torr, M. Pawan Kumar:
Provably Correct Physics-Informed Neural Networks. CoRR abs/2305.10157 (2023) - [i252]Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr, Adel Bibi:
Language Model Tokenizers Introduce Unfairness Between Languages. CoRR abs/2305.15425 (2023) - [i251]Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip H. S. Torr, Ser-Nam Lim:
Graph Inductive Biases in Transformers without Message Passing. CoRR abs/2305.17589 (2023) - [i250]Shuo Chen, Jindong Gu, Zhen Han, Yunpu Ma, Philip H. S. Torr, Volker Tresp:
Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models. CoRR abs/2306.02080 (2023) - [i249]Tom A. Lamb, Rudy Bunel, Krishnamurthy (Dj) Dvijotham, M. Pawan Kumar, Philip H. S. Torr, Francisco Eiras:
Faithful Knowledge Distillation. CoRR abs/2306.04431 (2023) - [i248]Wenqian Yu, Jindong Gu, Zhijiang Li, Philip H. S. Torr:
Reliable Evaluation of Adversarial Transferability. CoRR abs/2306.08565 (2023) - [i247]Shuyang Sun, Weijun Wang, Qihang Yu, Andrew G. Howard, Philip H. S. Torr, Liang-Chieh Chen:
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation. CoRR abs/2306.17319 (2023) - [i246]Runjia Li, Shuyang Sun, Mohamed Elhoseiny, Philip H. S. Torr:
OxfordTVG-HIC: Can Machine Make Humorous Captions from Images? CoRR abs/2307.11636 (2023) - [i245]Jindong Gu, Zhen Han, Shuo Chen, Ahmad Beirami, Bailan He, Gengyuan Zhang, Ruotong Liao, Yao Qin, Volker Tresp, Philip H. S. Torr:
A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models. CoRR abs/2307.12980 (2023) - [i244]Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip H. S. Torr, Dacheng Tao, Bernard Ghanem:
Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants. CoRR abs/2308.01746 (2023) - [i243]Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang:
Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer. CoRR abs/2308.08414 (2023) - [i242]Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr, Puneet K. Dokania:
Fine-tuning can cripple your foundation model; preserving features may be the solution. CoRR abs/2308.13320 (2023) - [i241]Jindong Gu, Fangyun Wei, Philip H. S. Torr, Han Hu:
Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks. CoRR abs/2309.06438 (2023) - [i240]Yang Zhang, Yawei Li, Hannah Brown, Mina Rezaei, Bernd Bischl, Philip H. S. Torr, Ashkan Khakzar, Kenji Kawaguchi:
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments. CoRR abs/2310.06514 (2023) - [i239]Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip H. S. Torr:
PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction. CoRR abs/2310.07449 (2023) - [i238]Luke Marks, Amir Abdullah, Luna Mendez, Rauno Arike, Philip H. S. Torr, Fazl Barez:
Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders. CoRR abs/2310.08164 (2023) - [i237]Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip H. S. Torr, Bo Zhao:
Real-Fake: Effective Training Data Synthesis Through Distribution Matching. CoRR abs/2310.10402 (2023) - [i236]Francisco Eiras, Kemal Oksuz, Adel Bibi, Philip H. S. Torr, Puneet K. Dokania:
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation. CoRR abs/2310.13479 (2023) - [i235]Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqian Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip H. S. Torr:
A Survey on Transferability of Adversarial Examples across Deep Neural Networks. CoRR abs/2310.17626 (2023) - [i234]Yoshua Bengio, Geoffrey E. Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian K. Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atilim Günes Baydin, Sheila A. McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca D. Dragan, Philip H. S. Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann:
Managing AI Risks in an Era of Rapid Progress. CoRR abs/2310.17688 (2023) - [i233]Zifu Wang, Maxim Berman, Amal Rannen Triki, Philip H. S. Torr, Devis Tuia, Tinne Tuytelaars, Luc Van Gool, Jiaqian Yu, Matthew B. Blaschko:
Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union. CoRR abs/2310.19252 (2023) - [i232]Aleksandar Petrov, Philip H. S. Torr, Adel Bibi:
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations. CoRR abs/2310.19698 (2023) - [i231]Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim, Bernard Ghanem, Philip H. S. Torr, Adel Bibi:
From Categories to Classifier: Name-Only Continual Learning by Exploring the Web. CoRR abs/2311.11293 (2023) - [i230]Hang Li, Chengzhi Shen, Philip H. S. Torr, Volker Tresp, Jindong Gu:
Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation. CoRR abs/2311.17216 (2023) - [i229]Shuo Chen, Zhen Han, Bailan He, Mark Buckley, Philip H. S. Torr, Volker Tresp, Jindong Gu:
Understanding and Improving In-Context Learning on Vision-language Models. CoRR abs/2311.18021 (2023) - [i228]Avery Ma, Amir-massoud Farahmand, Yangchen Pan, Philip H. S. Torr, Jindong Gu:
Improving Adversarial Transferability via Model Alignment. CoRR abs/2311.18495 (2023) - [i227]Botos Csaba, Wenxuan Zhang, Matthias Müller, Ser-Nam Lim, Mohamed Elhoseiny, Philip H. S. Torr, Adel Bibi:
Label Delay in Continual Learning. CoRR abs/2312.00923 (2023) - [i226]Shuyang Sun, Runjia Li, Philip H. S. Torr, Xiuye Gu, Siyang Li:
CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor. CoRR abs/2312.07661 (2023) - [i225]Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht:
Scene-Conditional 3D Object Stylization and Composition. CoRR abs/2312.12419 (2023) - [i224]Fazl Barez, Philip H. S. Torr:
Measuring Value Alignment. CoRR abs/2312.15241 (2023) - 2022
- [j72]Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge J. Belongie, Alan L. Yuille, Philip H. S. Torr, Song Bai:
Occluded Video Instance Segmentation: A Benchmark. Int. J. Comput. Vis. 130(8): 2022-2039 (2022) - [j71]Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip H. S. Torr, Raquel Urtasun, Jiaya Jia:
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation. IEEE Trans. Pattern Anal. Mach. Intell. 44(2): 969-984 (2022) - [j70]Francisco Eiras, Motasem Alfarra, Philip H. S. Torr, M. Pawan Kumar, Puneet K. Dokania, Bernard Ghanem, Adel Bibi:
ANCER: Anisotropic Certification via Sample-wise Volume Maximization. Trans. Mach. Learn. Res. 2022 (2022) - [c298]Motasem Alfarra, Juan C. Pérez, Ali K. Thabet, Adel Bibi, Philip H. S. Torr, Bernard Ghanem:
Combating Adversaries with Anti-adversaries. AAAI 2022: 5992-6000 - [c297]Motasem Alfarra, Adel Bibi, Naeemullah Khan, Philip H. S. Torr, Bernard Ghanem:
DeformRS: Certifying Input Deformations with Randomized Smoothing. AAAI 2022: 6001-6009 - [c296]Hongguang Zhang, Philip H. S. Torr, Piotr Koniusz:
Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer. ACCV (5) 2022: 3-20 - [c295]Saeid Naderiparizi, Adam Scibior, Andreas Munk, Mehrdad Ghadiri, Atilim Gunes Baydin, Bradley J. Gram-Hansen, Christian A. Schröder de Witt, Robert Zinkov, Philip H. S. Torr, Tom Rainforth, Yee Whye Teh, Frank Wood:
Amortized Rejection Sampling in Universal Probabilistic Programming. AISTATS 2022: 8392-8412 - [c294]Bowen Li, Philip H. S. Torr, Thomas Lukasiewicz:
Image-to-Image Translation with Text Guidance. BMVC 2022: 581 - [c293]Bowen Li, Philip H. S. Torr, Thomas Lukasiewicz:
Memory-Driven Text-to-Image Generation. BMVC 2022: 726 - [c292]Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Philip H. S. Torr, Guoying Zhao:
PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer. CVPR 2022: 4176-4186 - [c291]Kejie Li, Yansong Tang, Victor Adrian Prisacariu, Philip H. S. Torr:
BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion. CVPR 2022: 6156-6165 - [c290]Guangrun Wang, Yansong Tang, Liang Lin, Philip H. S. Torr:
Semantic-Aware Auto-Encoders for Self-supervised Representation Learning. CVPR 2022: 9654-9665 - [c289]Jieneng Chen, Shuyang Sun, Ju He, Philip H. S. Torr, Alan L. Yuille, Song Bai:
TransMix: Attend to Mix for Vision Transformers. CVPR 2022: 12125-12134 - [c288]Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip H. S. Torr, Song Bai, Vincent Y. F. Tan:
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning. CVPR 2022: 16701-16710 - [c287]Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr:
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation. CVPR 2022: 18134-18144 - [c286]Donglai Wei, Siddhant Kharbanda, Sarthak Arora, Roshan Roy, Nishant Jain, Akash Palrecha, Tanav Shah, Shray Mathur, Ritik Mathur, Abhijay Kemkar, Anirudh Srinivasan Chakravarthy, Zudi Lin, Won-Dong Jang, Yansong Tang, Song Bai, James Tompkin, Philip H. S. Torr, Hanspeter Pfister:
YouMVOS: An Actor-centric Multi-shot Video Object Segmentation Dataset. CVPR 2022: 21012-21021 - [c285]Motasem Alfarra, Juan C. Pérez, Anna Frühstück, Philip H. S. Torr, Peter Wonka, Bernard Ghanem:
On the Robustness of Quality Measures for GANs. ECCV (17) 2022: 18-33 - [c284]Chuhui Xue, Wenqing Zhang, Yu Hao, Shijian Lu, Philip H. S. Torr, Song Bai:
Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting. ECCV (28) 2022: 284-302 - [c283]Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip H. S. Torr:
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness. ECCV (29) 2022: 308-325 - [c282]Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania:
An Impartial Take to the CNN vs Transformer Robustness Contest. ECCV (13) 2022: 466-480 - [c281]Botos Csaba, Adel Bibi, Yanwei Li, Philip H. S. Torr, Ser-Nam Lim:
Diversified Dynamic Routing for Vision Tasks. ECCV Workshops (4) 2022: 756-772 - [c280]Tom Joy, Yuge Shi, Philip H. S. Torr, Tom Rainforth, Sebastian M. Schmon, Siddharth Narayanaswamy:
Learning Multimodal VAEs through Mutual Supervision. ICLR 2022 - [c279]A. Tuan Nguyen, Toan Tran, Yarin Gal, Philip H. S. Torr, Atilim Gunes Baydin:
KL Guided Domain Adaptation. ICLR 2022 - [c278]Yuge Shi, Jeffrey Seely, Philip H. S. Torr, Siddharth Narayanaswamy, Awni Y. Hannun, Nicolas Usunier, Gabriel Synnaeve:
Gradient Matching for Domain Generalization. ICLR 2022 - [c277]Yuge Shi, N. Siddharth, Philip H. S. Torr, Adam R. Kosiorek:
Adversarial Masking for Self-Supervised Learning. ICML 2022: 20026-20040 - [c276]Samuel Sokota, Christian A. Schröder de Witt, Maximilian Igl, Luisa M. Zintgraf, Philip H. S. Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob N. Foerster:
Communicating via Markov Decision Processes. ICML 2022: 20314-20328 - [c275]Dubing Chen, Yuming Shen, Haofeng Zhang, Philip H. S. Torr:
Zero-Shot Logit Adjustment. IJCAI 2022: 813-819 - [c274]Jiaguo Yu, Yuming Shen, Menghan Wang, Haofeng Zhang, Philip H. S. Torr:
Learning to Hash Naturally Sorts. IJCAI 2022: 1587-1593 - [c273]Ziyi Shen, Qianye Yang, Yuming Shen, Francesco Giganti, Vasilis Stavrinides, Richard E. Fan, Caroline M. Moore, Mirabela Rusu, Geoffrey A. Sonn, Philip H. S. Torr, Dean C. Barratt, Yipeng Hu:
Collaborative Quantization Embeddings for Intra-subject Prostate MR Image Registration. MICCAI (6) 2022: 237-247 - [c272]Bowen Li, Philip H. S. Torr, Thomas Lukasiewicz:
Clustering Generative Adversarial Networks for Story Visualization. ACM Multimedia 2022: 769-778 - [c271]Pau de Jorge Aranda, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. NeurIPS 2022 - [c270]Xipeng Chen, Guangrun Wang, Dizhong Zhu, Xiaodan Liang, Philip H. S. Torr, Liang Lin:
Structure-Preserving 3D Garment Modeling with Neural Sewing Machines. NeurIPS 2022 - [c269]Tim Franzmeyer, Philip H. S. Torr, João F. Henriques:
Learn what matters: cross-domain imitation learning with task-relevant embeddings. NeurIPS 2022 - [c268]A. Tuan Nguyen, Philip H. S. Torr, Ser Nam Lim:
FedSR: A Simple and Effective Domain Generalization Method for Federated Learning. NeurIPS 2022 - [c267]Francesco Pinto, Harry Yang, Ser Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness. NeurIPS 2022 - [c266]Menghan Wang, Yuchen Guo, Zhenqi Zhao, Guangzheng Hu, Yuming Shen, Mingming Gong, Philip H. S. Torr:
MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning. SIGIR 2022: 2105-2109 - [c265]Motasem Alfarra, Adel Bibi, Philip H. S. Torr, Bernard Ghanem:
Data dependent randomized smoothing. UAI 2022: 64-74 - [i223]Ming-Ming Cheng, Peng-Tao Jiang, Linghao Han, Liang Wang, Philip H. S. Torr:
Deeply Explain CNN via Hierarchical Decomposition. CoRR abs/2201.09205 (2022) - [i222]Motasem Alfarra, Juan C. Pérez, Anna Frühstück, Philip H. S. Torr, Peter Wonka, Bernard Ghanem:
On the Robustness of Quality Measures for GANs. CoRR abs/2201.13019 (2022) - [i221]Yuge Shi, N. Siddharth, Philip H. S. Torr, Adam R. Kosiorek:
Adversarial Masking for Self-Supervised Learning. CoRR abs/2201.13100 (2022) - [i220]Yuming Shen, Jiaguo Yu, Haofeng Zhang, Philip H. S. Torr, Menghan Wang:
Learning to Hash Naturally Sorts. CoRR abs/2201.13322 (2022) - [i219]Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. CoRR abs/2202.01181 (2022) - [i218]Atilim Günes Baydin, Barak A. Pearlmutter, Don Syme, Frank Wood, Philip H. S. Torr:
Gradients without Backpropagation. CoRR abs/2202.08587 (2022) - [i217]Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe:
Local and Global GANs with Semantic-Aware Upsampling for Image Generation. CoRR abs/2203.00047 (2022) - [i216]Chuhui Xue, Yu Hao, Shijian Lu, Philip H. S. Torr, Song Bai:
Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting. CoRR abs/2203.03911 (2022) - [i215]A. Tuan Nguyen, Ser Nam Lim, Philip H. S. Torr:
Task-Agnostic Robust Representation Learning. CoRR abs/2203.07596 (2022) - [i214]Kejie Li, Yansong Tang, Victor Adrian Prisacariu, Philip H. S. Torr:
BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion. CoRR abs/2204.01139 (2022) - [i213]Menghan Wang, Yuchen Guo, Zhenqi Zhao, Guangzheng Hu, Yuming Shen, Mingming Gong, Philip H. S. Torr:
MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning. CoRR abs/2204.08326 (2022) - [i212]Feihu Zhang, Vladlen Koltun, Philip H. S. Torr, René Ranftl, Stephan R. Richter:
Unsupervised Contrastive Domain Adaptation for Semantic Segmentation. CoRR abs/2204.08399 (2022) - [i211]Dubing Chen, Yuming Shen, Haofeng Zhang, Philip H. S. Torr:
Towards the Semantic Weak Generalization Problem in Generative Zero-Shot Learning: Ante-hoc and Post-hoc. CoRR abs/2204.11280 (2022) - [i210]Dubing Chen, Yuming Shen, Haofeng Zhang, Philip H. S. Torr:
Zero-Shot Logit Adjustment. CoRR abs/2204.11822 (2022) - [i209]Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Grégory Rogez, Philip H. S. Torr:
Catastrophic overfitting is a bug but also a feature. CoRR abs/2206.08242 (2022) - [i208]Yuge Shi, Imant Daunhawer, Julia E. Vogt, Philip H. S. Torr, Amartya Sanyal:
How robust are pre-trained models to distribution shift? CoRR abs/2206.08871 (2022) - [i207]Francesco Pinto, Harry Yang, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness. CoRR abs/2206.14502 (2022) - [i206]Weiming Hu, Qiang Wang, Li Zhang, Luca Bertinetto, Philip H. S. Torr:
SiamMask: A Framework for Fast Online Object Tracking and Segmentation. CoRR abs/2207.02088 (2022) - [i205]Ziyi Shen, Qianye Yang, Yuming Shen, Francesco Giganti, Vasilis Stavrinides, Richard E. Fan, Caroline M. Moore, Mirabela Rusu, Geoffrey A. Sonn, Philip H. S. Torr, Dean C. Barratt, Yipeng Hu:
Collaborative Quantization Embeddings for Intra-Subject Prostate MR Image Registration. CoRR abs/2207.06189 (2022) - [i204]Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip H. S. Torr, Puneet K. Dokania:
Sample-dependent Adaptive Temperature Scaling for Improved Calibration. CoRR abs/2207.06211 (2022) - [i203]Xiaogang Xu, Hengshuang Zhao, Philip H. S. Torr:
Universal Adaptive Data Augmentation. CoRR abs/2207.06658 (2022) - [i202]Tim Franzmeyer, João F. Henriques, Jakob N. Foerster, Philip H. S. Torr, Adel Bibi, Christian Schröder de Witt:
Illusionary Attacks on Sequential Decision Makers and Countermeasures. CoRR abs/2207.10170 (2022) - [i201]Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania:
An Impartial Take to the CNN vs Transformer Robustness Contest. CoRR abs/2207.11347 (2022) - [i200]Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip H. S. Torr:
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness. CoRR abs/2207.12391 (2022) - [i199]Bowen Li, Philip H. S. Torr, Thomas Lukasiewicz:
Memory-Driven Text-to-Image Generation. CoRR abs/2208.07022 (2022) - [i198]Li Zhang, Mohan Chen, Anurag Arnab, Xiangyang Xue, Philip H. S. Torr:
Dynamic Graph Message Passing Networks for Visual Recognition. CoRR abs/2209.09760 (2022) - [i197]Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen, Ashish Shah, Philip H. S. Torr, Puneet K. Dokania, Ser-Nam Lim:
Raising the Bar on the Evaluation of Out-of-Distribution Detection. CoRR abs/2209.11960 (2022) - [i196]Tim Franzmeyer, Philip H. S. Torr, João F. Henriques:
Learn what matters: cross-domain imitation learning with task-relevant embeddings. CoRR abs/2209.12093 (2022) - [i195]Botos Csaba, Adel Bibi, Yanwei Li, Philip H. S. Torr, Ser-Nam Lim:
Diversified Dynamic Routing for Vision Tasks. CoRR abs/2209.13071 (2022) - [i194]Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip H. S. Torr, Song Bai, Xiaojuan Qi:
Is synthetic data from generative models ready for image recognition? CoRR abs/2210.07574 (2022) - [i193]Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr:
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning. CoRR abs/2210.12971 (2022) - [i192]Xipeng Chen, Guangrun Wang, Dizhong Zhu, Xiaodan Liang, Philip H. S. Torr, Liang Lin:
Structure-Preserving 3D Garment Modeling with Neural Sewing Machines. CoRR abs/2211.06701 (2022) - [i191]Hao Tang, Ling Shao, Philip H. S. Torr, Nicu Sebe:
Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis. CoRR abs/2211.06719 (2022) - [i190]Guangrun Wang, Philip H. S. Torr:
Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs. CoRR abs/2211.14794 (2022) - [i189]Shuyang Sun, Jieneng Chen, Ruifei He, Alan L. Yuille, Philip H. S. Torr, Song Bai:
LUMix: Improving Mixup by Better Modelling Label Uncertainty. CoRR abs/2211.15846 (2022) - [i188]Jishnu Mukhoti, Tsung-Yu Lin, Omid Poursaeed, Rui Wang, Ashish Shah, Philip H. S. Torr, Ser-Nam Lim:
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning. CoRR abs/2212.04994 (2022) - [i187]Xiaogang Xu, Hengshuang Zhao, Philip H. S. Torr, Jiaya Jia:
General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments. CoRR abs/2212.05387 (2022) - [i186]Jianhao Yuan, Francesco Pinto, Adam Davies, Aarushi Gupta, Philip H. S. Torr:
Not Just Pretty Pictures: Text-to-Image Generators Enable Interpretable Interventions for Robust Representations. CoRR abs/2212.11237 (2022) - 2021
- [j69]Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip H. S. Torr, Andreas Geiger, Laura Leal-Taixé, Bastian Leibe:
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking. Int. J. Comput. Vis. 129(2): 548-578 (2021) - [j68]Cong Fang, Song Bai, Qianlan Chen, Yu Zhou, Liming Xia, Lixin Qin, Shi Gong, Xudong Xie, Chunhua Zhou, Dandan Tu, Changzheng Zhang, Xiaowu Liu, Weiwei Chen, Xiang Bai, Philip H. S. Torr:
Deep learning for predicting COVID-19 malignant progression. Medical Image Anal. 72: 102096 (2021) - [j67]Shanghua Gao, Ming-Ming Cheng, Kai Zhao, Xinyu Zhang, Ming-Hsuan Yang, Philip H. S. Torr:
Res2Net: A New Multi-Scale Backbone Architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43(2): 652-662 (2021) - [j66]Nan Xue, Song Bai, Fu-Dong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang, Philip H. S. Torr:
Learning Regional Attraction for Line Segment Detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(6): 1998-2013 (2021) - [j65]Song Bai, Yingwei Li, Yuyin Zhou, Qizhu Li, Philip H. S. Torr:
Adversarial Metric Attack and Defense for Person Re-Identification. IEEE Trans. Pattern Anal. Mach. Intell. 43(6): 2119-2126 (2021) - [j64]Song Bai, Feihu Zhang, Philip H. S. Torr:
Hypergraph convolution and hypergraph attention. Pattern Recognit. 110: 107637 (2021) - [c264]Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz:
Using Hindsight to Anchor Past Knowledge in Continual Learning. AAAI 2021: 6993-7001 - [c263]Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania:
Mirror Descent View for Neural Network Quantization. AISTATS 2021: 2809-2817 - [c262]Zhao Yang, Yansong Tang, Luca Bertinetto, Hengshuang Zhao, Philip H. S. Torr:
Hierarchical Interaction Network for Video Object Segmentation from Referring Expressions. BMVC 2021: 254 - [c261]Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H. S. Torr, Li Zhang:
Rethinking Semantic Segmentation From a Sequence-to-Sequence Perspective With Transformers. CVPR 2021: 6881-6890 - [c260]Hongguang Zhang, Piotr Koniusz, Songlei Jian, Hongdong Li, Philip H. S. Torr:
Rethinking Class Relations: Absolute-Relative Supervised and Unsupervised Few-Shot Learning. CVPR 2021: 9432-9441 - [c259]Xiaolong Liu, Yao Hu, Song Bai, Fei Ding, Xiang Bai, Philip H. S. Torr:
Multi-Shot Temporal Event Localization: A Benchmark. CVPR 2021: 12596-12606 - [c258]Oscar Rahnama, Stuart Golodetz, Tommaso Cavallari, Philip H. S. Torr:
Scalable FPGA Median Filtering via a Directional Median Cascade. FCCM 2021: 273 - [c257]Xiaoyu Yue, Shuyang Sun, Zhanghui Kuang, Meng Wei, Philip H. S. Torr, Wayne Zhang, Dahua Lin:
Vision Transformer with Progressive Sampling. ICCV 2021: 377-386 - [c256]Shuyang Sun, Xiaoyu Yue, Xiaojuan Qi, Wanli Ouyang, Victor Prisacariu, Philip H. S. Torr:
Aggregation with Feature Detection. ICCV 2021: 507-516 - [c255]Guangrun Wang, Keze Wang, Guangcong Wang, Philip H. S. Torr, Liang Lin:
Solving Inefficiency of Self-supervised Representation Learning. ICCV 2021: 9485-9495 - [c254]Feihu Zhang, Oliver J. Woodford, Victor Prisacariu, Philip H. S. Torr:
Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation. ICCV 2021: 10787-10797 - [c253]Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip H. S. Torr, Vladlen Koltun:
Point Transformer. ICCV 2021: 16239-16248 - [c252]Angira Sharma, Naeemullah Khan, Muhammad Mubashar, Ganesh Sundaramoorthi, Philip H. S. Torr:
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation. ICCVW 2021: 1621-1630 - [c251]Matej Kristan, Jirí Matas, Ales Leonardis, Michael Felsberg, Roman P. Pflugfelder, Joni-Kristian Kämäräinen, Hyung Jin Chang, Martin Danelljan, Luka Cehovin Zajc, Alan Lukezic, Ondrej Drbohlav, Jani Käpylä, Gustav Häger, Song Yan, Jinyu Yang, Zhongqun Zhang, Gustavo Fernández, Mohamed H. Abdelpakey, Goutam Bhat, Llukman Cerkezi, Hakan Cevikalp, Shengyong Chen, Xin Chen, Miao Cheng, Ziyi Cheng, Yu-Chen Chiu, Ozgun Cirakman, Yutao Cui, Kenan Dai, Mohana Murali Dasari, Qili Deng, Xingping Dong, Daniel K. Du, Matteo Dunnhofer, Zhenhua Feng, Zhiyong Feng, Zhihong Fu, Shiming Ge, Rama Krishna Gorthi, Yuzhang Gu, Bilge Günsel, Qing Guo, Filiz Gurkan, Wencheng Han, Yanyan Huang, Felix Järemo Lawin, Shang-Jhih Jhang, Rongrong Ji, Cheng Jiang, Yingjie Jiang, Felix Juefei-Xu, J. Yin, Xiao Ke, Fahad Shahbaz Khan, Byeong Hak Kim, Josef Kittler, Xiangyuan Lan, Jun Ha Lee, Bastian Leibe, Hui Li, Jianhua Li, Xianxian Li, Yuezhou Li, Bo Liu, Chang Liu, Jingen Liu, Li Liu, Qingjie Liu, Huchuan Lu, Wei Lu, Jonathon Luiten, Jie Ma, Ziang Ma, Niki Martinel, Christoph Mayer, Alireza Memarmoghadam, Christian Micheloni, Yuzhen Niu, Danda Pani Paudel, Houwen Peng, Shoumeng Qiu, Aravindh Rajiv, Muhammad Rana, Andreas Robinson, Hasan Saribas, Ling Shao, Mohamed S. Shehata, Furao Shen, Jianbing Shen, Kristian Simonato, Xiaoning Song, Zhangyong Tang, Radu Timofte, Philip H. S. Torr, Chi-Yi Tsai, Bedirhan Uzun, Luc Van Gool, Paul Voigtlaender, Dong Wang, Guangting Wang, Liangliang Wang, Lijun Wang, Limin Wang, Linyuan Wang, Yong Wang, Yunhong Wang, Chenyan Wu, Gangshan Wu, Xiaojun Wu, Fei Xie, Tianyang Xu, Xiang Xu, Wanli Xue, Bin Yan, Wankou Yang, Xiaoyun Yang, Yu Ye, Jun Yin, Chengwei Zhang, Chunhui Zhang, Haitao Zhang, Kaihua Zhang, Kangkai Zhang, Xiaohan Zhang, Xiaolin Zhang, Xinyu Zhang, Zhibin Zhang, Shao-Chuan Zhao, Ming Zhen, Bineng Zhong, Jiawen Zhu, Xuefeng Zhu:
The Ninth Visual Object Tracking VOT2021 Challenge Results. ICCVW 2021: 2711-2738 - [c250]Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Progressive Skeletonization: Trimming more fat from a network at initialization. ICLR 2021 - [c249]Tom Joy, Sebastian M. Schmon, Philip H. S. Torr, Siddharth Narayanaswamy, Tom Rainforth:
Capturing Label Characteristics in VAEs. ICLR 2021 - [c248]Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr, Martin Jaggi:
Understanding the effects of data parallelism and sparsity on neural network training. ICLR 2021 - [c247]Alessandro De Palma, Harkirat S. Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar:
Scaling the Convex Barrier with Active Sets. ICLR 2021 - [c246]Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr:
How Benign is Benign Overfitting ? ICLR 2021 - [c245]Yuge Shi, Brooks Paige, Philip H. S. Torr, N. Siddharth:
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models. ICLR 2021 - [c244]Bei Peng, Tabish Rashid, Christian Schröder de Witt, Pierre-Alexandre Kamienny, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson:
FACMAC: Factored Multi-Agent Centralised Policy Gradients. NeurIPS 2021: 12208-12221 - [c243]Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge J. Belongie, Alan L. Yuille, Philip H. S. Torr, Song Bai:
Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge. NeurIPS Datasets and Benchmarks 2021 - [c242]Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H. S. Torr, Luca Bertinetto:
Do Different Tracking Tasks Require Different Appearance Models? NeurIPS 2021: 726-738 - [c241]Feihu Zhang, Philip H. S. Torr, René Ranftl, Stephan R. Richter:
Looking Beyond Single Images for Contrastive Semantic Segmentation Learning. NeurIPS 2021: 3285-3297 - [c240]Harkirat Singh Behl, M. Pawan Kumar, Philip H. S. Torr, Krishnamurthy Dvijotham:
Overcoming the Convex Barrier for Simplex Inputs. NeurIPS 2021: 4871-4882 - [c239]Keyu Tian, Chen Lin, Ser-Nam Lim, Wanli Ouyang, Puneet K. Dokania, Philip H. S. Torr:
A Continuous Mapping For Augmentation Design. NeurIPS 2021: 13732-13743 - [c238]Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip H. S. Torr, Ling Shao:
You Never Cluster Alone. NeurIPS 2021: 27734-27746 - [i185]Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H. S. Torr, M. Pawan Kumar:
Scaling the Convex Barrier with Sparse Dual Algorithms. CoRR abs/2101.05844 (2021) - [i184]Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge J. Belongie, Alan L. Yuille, Philip H. S. Torr, Song Bai:
Occluded Video Instance Segmentation. CoRR abs/2102.01558 (2021) - [i183]Naeemullah Khan, Angira Sharma, Ganesh Sundaramoorthi, Philip H. S. Torr:
Shape-Tailored Deep Neural Networks. CoRR abs/2102.08497 (2021) - [i182]Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal:
Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty. CoRR abs/2102.11582 (2021) - [i181]Motasem Alfarra, Juan C. Pérez, Ali K. Thabet, Adel Bibi, Philip H. S. Torr, Bernard Ghanem:
Combating Adversaries with Anti-Adversaries. CoRR abs/2103.14347 (2021) - [i180]Bin Ren, Hao Tang, Fanyang Meng, Runwei Ding, Ling Shao, Philip H. S. Torr, Nicu Sebe:
Cloth Interactive Transformer for Virtual Try-On. CoRR abs/2104.05519 (2021) - [i179]Alessandro De Palma, Rudy Bunel, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar:
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition. CoRR abs/2104.06718 (2021) - [i178]Guangrun Wang, Keze Wang, Guangcong Wang, Philip H. S. Torr, Liang Lin:
Solving Inefficiency of Self-supervised Representation Learning. CoRR abs/2104.08760 (2021) - [i177]Yuge Shi, Jeffrey Seely, Philip H. S. Torr, N. Siddharth, Awni Y. Hannun, Nicolas Usunier, Gabriel Synnaeve:
Gradient Matching for Domain Generalization. CoRR abs/2104.09937 (2021) - [i176]Yansong Tang, Zhenyu Jiang, Zhenda Xie, Yue Cao, Zheng Zhang, Philip H. S. Torr, Han Hu:
Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning. CoRR abs/2105.05838 (2021) - [i175]Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip H. S. Torr, Ling Shao:
You Never Cluster Alone. CoRR abs/2106.01908 (2021) - [i174]Shanghua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip H. S. Torr:
Large-scale Unsupervised Semantic Segmentation. CoRR abs/2106.03149 (2021) - [i173]A. Tuan Nguyen, Toan Tran, Yarin Gal, Philip H. S. Torr, Atilim Günes Baydin:
KL Guided Domain Adaptation. CoRR abs/2106.07780 (2021) - [i172]Tom Joy, Yuge Shi, Philip H. S. Torr, Tom Rainforth, Sebastian M. Schmon, N. Siddharth:
Learning Multimodal VAEs through Mutual Supervision. CoRR abs/2106.12570 (2021) - [i171]Motasem Alfarra, Adel Bibi, Naeemullah Khan, Philip H. S. Torr, Bernard Ghanem:
DeformRS: Certifying Input Deformations with Randomized Smoothing. CoRR abs/2107.00996 (2021) - [i170]Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H. S. Torr, Luca Bertinetto:
Do Different Tracking Tasks Require Different Appearance Models? CoRR abs/2107.02156 (2021) - [i169]Francisco Eiras, Motasem Alfarra, M. Pawan Kumar, Philip H. S. Torr, Puneet K. Dokania, Bernard Ghanem, Adel Bibi:
ANCER: Anisotropic Certification via Sample-wise Volume Maximization. CoRR abs/2107.04570 (2021) - [i168]Shuyang Sun, Xiaoyu Yue, Song Bai, Philip H. S. Torr:
Visual Parser: Representing Part-whole Hierarchies with Transformers. CoRR abs/2107.05790 (2021) - [i167]Samuel Sokota, Christian Schröder de Witt, Maximilian Igl, Luisa M. Zintgraf, Philip H. S. Torr, Shimon Whiteson, Jakob N. Foerster:
Implicit Communication as Minimum Entropy Coupling. CoRR abs/2107.08295 (2021) - [i166]Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip H. S. Torr, Jiaya Jia:
Open-World Entity Segmentation. CoRR abs/2107.14228 (2021) - [i165]Botos Csaba, Xiaojuan Qi, Arslan Chaudhry, Puneet K. Dokania, Philip H. S. Torr:
Multilevel Knowledge Transfer for Cross-Domain Object Detection. CoRR abs/2108.00977 (2021) - [i164]Xiaoyu Yue, Shuyang Sun, Zhanghui Kuang, Meng Wei, Philip H. S. Torr, Wayne Zhang, Dahua Lin:
Vision Transformer with Progressive Sampling. CoRR abs/2108.01684 (2021) - [i163]Angira Sharma, Naeemullah Khan, Muhammad Mubashar, Ganesh Sundaramoorthi, Philip H. S. Torr:
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation. CoRR abs/2108.04226 (2021) - [i162]Shiyu Tang, Ruihao Gong, Yan Wang, Aishan Liu, Jiakai Wang, Xinyun Chen, Fengwei Yu, Xianglong Liu, Dawn Song, Alan L. Yuille, Philip H. S. Torr, Dacheng Tao:
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques. CoRR abs/2109.05211 (2021) - [i161]Andrew Gambardella, Bogdan State, Naeemullah Khan, Leo Tsourides, Philip H. S. Torr, Atilim Günes Baydin:
Detecting and Quantifying Malicious Activity with Simulation-based Inference. CoRR abs/2110.02483 (2021) - [i160]Jishnu Mukhoti, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal:
Deep Deterministic Uncertainty for Semantic Segmentation. CoRR abs/2111.00079 (2021) - [i159]Roy Henha Eyono, Fabio Maria Carlucci, Pedro M. Esperança, Binxin Ru, Philip H. S. Torr:
AUTOKD: Automatic Knowledge Distillation Into A Student Architecture Family. CoRR abs/2111.03555 (2021) - [i158]Jiyang Qi, Yan Gao, Yao Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge J. Belongie, Alan L. Yuille, Philip H. S. Torr, Song Bai:
Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge. CoRR abs/2111.07950 (2021) - [i157]Jieneng Chen, Shuyang Sun, Ju He, Philip H. S. Torr, Alan L. Yuille, Song Bai:
TransMix: Attend to Mix for Vision Transformers. CoRR abs/2111.09833 (2021) - [i156]Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip H. S. Torr:
Adversarial Examples on Segmentation Models Can be Easy to Transfer. CoRR abs/2111.11368 (2021) - [i155]Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Philip H. S. Torr, Guoying Zhao:
PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer. CoRR abs/2111.12082 (2021) - [i154]Christian Schröder de Witt, Yongchao Huang, Philip H. S. Torr, Martin Strohmeier:
Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS. CoRR abs/2111.12197 (2021) - [i153]Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H. S. Torr:
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation. CoRR abs/2112.02244 (2021) - [i152]Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip H. S. Torr, Song Bai, Vincent Y. F. Tan:
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning. CoRR abs/2112.04731 (2021) - 2020
- [j63]Rodrigo Andrade de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, Adnane Boukhayma, N. Siddharth, Philip H. S. Torr:
DGPose: Deep Generative Models for Human Body Analysis. Int. J. Comput. Vis. 128(5): 1537-1563 (2020) - [j62]Rudy Bunel, Jingyue Lu, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, M. Pawan Kumar:
Branch and Bound for Piecewise Linear Neural Network Verification. J. Mach. Learn. Res. 21: 42:1-42:39 (2020) - [j61]Juan-Manuel Pérez-Rúa, Ondrej Miksik, Tomás Crivelli, Patrick Bouthemy, Philip H. S. Torr, Patrick Pérez:
ROAM: A Rich Object Appearance Model with Application to Rotoscoping. IEEE Trans. Pattern Anal. Mach. Intell. 42(8): 1996-2010 (2020) - [j60]Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord, Julien P. C. Valentin, Victor Adrian Prisacariu, Luigi Di Stefano, Philip H. S. Torr:
Real-Time RGB-D Camera Pose Estimation in Novel Scenes Using a Relocalisation Cascade. IEEE Trans. Pattern Anal. Mach. Intell. 42(10): 2465-2477 (2020) - [j59]Anurag Arnab, Ondrej Miksik, Philip H. S. Torr:
On the Robustness of Semantic Segmentation Models to Adversarial Attacks. IEEE Trans. Pattern Anal. Mach. Intell. 42(12): 3040-3053 (2020) - [c237]Hao Tang, Song Bai, Philip H. S. Torr, Nicu Sebe:
Bipartite Graph Reasoning GANs for Person Image Generation. BMVC 2020 - [c236]Nan Xue, Tianfu Wu, Song Bai, Fudong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr:
Holistically-Attracted Wireframe Parsing. CVPR 2020: 2785-2794 - [c235]Li Zhang, Dan Xu, Anurag Arnab, Philip H. S. Torr:
Dynamic Graph Message Passing Networks. CVPR 2020: 3723-3732 - [c234]Victoria Fernández Abrevaya, Adnane Boukhayma, Philip H. S. Torr, Edmond Boyer:
Cross-Modal Deep Face Normals With Deactivable Skip Connections. CVPR 2020: 4978-4988 - [c233]Paul Voigtlaender, Jonathon Luiten, Philip H. S. Torr, Bastian Leibe:
Siam R-CNN: Visual Tracking by Re-Detection. CVPR 2020: 6577-6587 - [c232]Hao Tang, Dan Xu, Yan Yan, Philip H. S. Torr, Nicu Sebe:
Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation. CVPR 2020: 7867-7876 - [c231]Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr:
ManiGAN: Text-Guided Image Manipulation. CVPR 2020: 7877-7886 - [c230]Zhengzhe Liu, Xiaojuan Qi, Philip H. S. Torr:
Global Texture Enhancement for Fake Face Detection in the Wild. CVPR 2020: 8057-8066 - [c229]Qizhu Li, Xiaojuan Qi, Philip H. S. Torr:
Unifying Training and Inference for Panoptic Segmentation. CVPR 2020: 13317-13325 - [c228]Carlo Biffi, Steven McDonagh, Philip H. S. Torr, Ales Leonardis, Sarah Parisot:
Many-Shot from Low-Shot: Learning to Annotate Using Mixed Supervision for Object Detection. ECCV (8) 2020: 35-50 - [c227]Harkirat Singh Behl, Atilim Günes Baydin, Ran Gal, Philip H. S. Torr, Vibhav Vineet:
AutoSimulate: (Quickly) Learning Synthetic Data Generation. ECCV (22) 2020: 255-271 - [c226]Viveka Kulharia, Siddhartha Chandra, Amit Agrawal, Philip H. S. Torr, Ambrish Tyagi:
Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised Segmentation. ECCV (27) 2020: 290-308 - [c225]Feihu Zhang, Xiaojuan Qi, Ruigang Yang, Victor Prisacariu, Benjamin W. Wah, Philip H. S. Torr:
Domain-Invariant Stereo Matching Networks. ECCV (2) 2020: 420-439 - [c224]Ameya Prabhu, Philip H. S. Torr, Puneet K. Dokania:
GDumb: A Simple Approach that Questions Our Progress in Continual Learning. ECCV (2) 2020: 524-540 - [c223]Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip H. S. Torr, Piotr Koniusz:
Few-Shot Action Recognition with Permutation-Invariant Attention. ECCV (5) 2020: 525-542 - [c222]Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Joni-Kristian Kämäräinen, Martin Danelljan, Luka Cehovin Zajc, Alan Lukezic, Ondrej Drbohlav, Linbo He, Yushan Zhang, Song Yan, Jinyu Yang, Gustavo Fernández, Alexander G. Hauptmann, Alireza Memarmoghadam, Álvaro García-Martín, Andreas Robinson, Anton Varfolomieiev, Awet Haileslassie Gebrehiwot, Bedirhan Uzun, Bin Yan, Bing Li, Chen Qian, Chi-Yi Tsai, Christian Micheloni, Dong Wang, Fei Wang, Fei Xie, Felix Järemo Lawin, Fredrik Gustafsson, Gian Luca Foresti, Goutam Bhat, Guangqi Chen, Haibin Ling, Haitao Zhang, Hakan Cevikalp, Haojie Zhao, Haoran Bai, Hari Chandana Kuchibhotla, Hasan Saribas, Heng Fan, Hossein Ghanei-Yakhdan, Houqiang Li, Houwen Peng, Huchuan Lu, Hui Li, Javad Khaghani, Jesús Bescós, Jianhua Li, Jianlong Fu, Jiaqian Yu, Jingtao Xu, Josef Kittler, Jun Yin, Junhyun Lee, Kaicheng Yu, Kaiwen Liu, Kang Yang, Kenan Dai, Li Cheng, Li Zhang, Lijun Wang, Linyuan Wang, Luc Van Gool, Luca Bertinetto, Matteo Dunnhofer, Miao Cheng, Mohana Murali Dasari, Ning Wang, Pengyu Zhang, Philip H. S. Torr, Qiang Wang, Radu Timofte, Rama Krishna Sai Subrahmanyam Gorthi, Seokeon Choi, Seyed Mojtaba Marvasti-Zadeh, Shao-Chuan Zhao, Shohreh Kasaei, Shoumeng Qiu, Shuhao Chen, Thomas B. Schön, Tianyang Xu, Wei Lu, Weiming Hu, Wengang Zhou, Xi Qiu, Xiao Ke, Xiao-Jun Wu, Xiaolin Zhang, Xiaoyun Yang, Xuefeng Zhu, Yingjie Jiang, Yingming Wang, Yiwei Chen, Yu Ye, Yuezhou Li, Yuncon Yao, Yunsung Lee, Yuzhang Gu, Zezhou Wang, Zhangyong Tang, Zhenhua Feng, Zhijun Mai, Zhipeng Zhang, Zhirong Wu, Ziang Ma:
The Eighth Visual Object Tracking VOT2020 Challenge Results. ECCV Workshops (5) 2020: 547-601 - [c221]Feihu Zhang, Jin Fang, Benjamin W. Wah, Philip H. S. Torr:
Deep FusionNet for Point Cloud Semantic Segmentation. ECCV (24) 2020: 644-663 - [c220]Hao Tang, Song Bai, Li Zhang, Philip H. S. Torr, Nicu Sebe:
XingGAN for Person Image Generation. ECCV (25) 2020: 717-734 - [c219]Oscar Rahnama, Tommaso Cavallari, Philip H. S. Torr, Stuart Golodetz:
Scalable FPGA Median Filtering using Multiple Efficient Passes. FPGA 2020: 313 - [c218]Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr:
A Signal Propagation Perspective for Pruning Neural Networks at Initialization. ICLR 2020 - [c217]Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania:
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. ICLR 2020 - [c216]Francesco Pinto, Andrea Romanoni, Matteo Matteucci, Philip H. S. Torr:
SECI-GAN: Semantic and Edge Completion for dynamic objects removal. ICPR 2020: 10441-10448 - [c215]Feihu Zhang, Chenye Guan, Jin Fang, Song Bai, Ruigang Yang, Philip H. S. Torr, Victor Prisacariu:
Instance Segmentation of LiDAR Point Clouds. ICRA 2020: 9448-9455 - [c214]Harkirat Singh Behl, Mohammad Najafi, Anurag Arnab, Philip H. S. Torr:
Meta-Learning Deep Visual Words for Fast Video Object Segmentation. IROS 2020: 8484-8491 - [c213]Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr:
Continual Learning in Low-rank Orthogonal Subspaces. NeurIPS 2020 - [c212]Arnab Ghosh, Harkirat S. Behl, Emilien Dupont, Philip H. S. Torr, Vinay P. Namboodiri:
STEER : Simple Temporal Regularization For Neural ODE. NeurIPS 2020 - [c211]Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz:
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation. NeurIPS 2020 - [c210]Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania:
Calibrating Deep Neural Networks using Focal Loss. NeurIPS 2020 - [c209]Rudy Bunel, Alessandro De Palma, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar:
Lagrangian Decomposition for Neural Network Verification. UAI 2020: 370-379 - [c208]Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr:
Devon: Deformable Volume Network for Learning Optical Flow. WACV 2020: 2694-2702 - [i151]Hongguang Zhang, Philip H. S. Torr, Piotr Koniusz:
Few-shot Learning with Multi-scale Self-supervision. CoRR abs/2001.01600 (2020) - [i150]Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip H. S. Torr, Piotr Koniusz:
Few-shot Action Recognition via Improved Attention with Self-supervision. CoRR abs/2001.03905 (2020) - [i149]Hongguang Zhang, Philip H. S. Torr, Hongdong Li, Songlei Jian, Piotr Koniusz:
Rethinking Class Relations: Absolute-relative Few-shot Learning. CoRR abs/2001.03919 (2020) - [i148]Qizhu Li, Xiaojuan Qi, Philip H. S. Torr:
Unifying Training and Inference for Panoptic Segmentation. CoRR abs/2001.04982 (2020) - [i147]Zhengzhe Liu, Xiaojuan Qi, Jiaya Jia, Philip H. S. Torr:
Global Texture Enhancement for Fake Face Detection in the Wild. CoRR abs/2002.00133 (2020) - [i146]Hao Tang, Dan Xu, Yan Yan, Jason J. Corso, Philip H. S. Torr, Nicu Sebe:
Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation. CoRR abs/2002.01048 (2020) - [i145]Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz:
Image-to-Image Translation with Text Guidance. CoRR abs/2002.05235 (2020) - [i144]Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip H. S. Torr, David Lopez-Paz:
Using Hindsight to Anchor Past Knowledge in Continual Learning. CoRR abs/2002.08165 (2020) - [i143]Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip H. S. Torr, Puneet K. Dokania:
Calibrating Deep Neural Networks using Focal Loss. CoRR abs/2002.09437 (2020) - [i142]Rudy Bunel, Alessandro De Palma, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar:
Lagrangian Decomposition for Neural Network Verification. CoRR abs/2002.10410 (2020) - [i141]Nan Xue, Tianfu Wu, Song Bai, Fu-Dong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr:
Holistically-Attracted Wireframe Parsing. CoRR abs/2003.01663 (2020) - [i140]Christian Schröder de Witt, Bei Peng, Pierre-Alexandre Kamienny, Philip H. S. Torr, Wendelin Böhmer, Shimon Whiteson:
Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control. CoRR abs/2003.06709 (2020) - [i139]Victoria Fernández Abrevaya, Adnane Boukhayma, Philip H. S. Torr, Edmond Boyer:
Cross-modal Deep Face Normals with Deactivable Skip Connections. CoRR abs/2003.09691 (2020) - [i138]Namhoon Lee, Philip H. S. Torr, Martin Jaggi:
Data Parallelism in Training Sparse Neural Networks. CoRR abs/2003.11316 (2020) - [i137]Hao Tang, Xiaojuan Qi, Dan Xu, Philip H. S. Torr, Nicu Sebe:
Edge Guided GANs with Semantic Preserving for Semantic Image Synthesis. CoRR abs/2003.13898 (2020) - [i136]Daniela Massiceti, Viveka Kulharia, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr:
A Revised Generative Evaluation of Visual Dialogue. CoRR abs/2004.09272 (2020) - [i135]Christian Schröder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Robert Zinkov, Puneet K. Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip H. S. Torr, Atilim Günes Baydin:
Simulation-Based Inference for Global Health Decisions. CoRR abs/2005.07062 (2020) - [i134]Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Grégory Rogez, Puneet K. Dokania:
Progressive Skeletonization: Trimming more fat from a network at initialization. CoRR abs/2006.09081 (2020) - [i133]Tom Joy, Sebastian M. Schmon, Philip H. S. Torr, N. Siddharth, Tom Rainforth:
Rethinking Semi-Supervised Learning in VAEs. CoRR abs/2006.10102 (2020) - [i132]Arnab Ghosh, Harkirat Singh Behl, Emilien Dupont, Philip H. S. Torr, Vinay P. Namboodiri:
STEER : Simple Temporal Regularization For Neural ODEs. CoRR abs/2006.10711 (2020) - [i131]Yuge Shi, Brooks Paige, Philip H. S. Torr, N. Siddharth:
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models. CoRR abs/2007.01179 (2020) - [i130]Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip H. S. Torr:
How benign is benign overfitting? CoRR abs/2007.04028 (2020) - [i129]Minqi Jiang, Jelena Luketina, Nantas Nardelli, Pasquale Minervini, Philip H. S. Torr, Shimon Whiteson, Tim Rocktäschel:
WordCraft: An Environment for Benchmarking Commonsense Agents. CoRR abs/2007.09185 (2020) - [i128]Hao Tang, Song Bai, Li Zhang, Philip H. S. Torr, Nicu Sebe:
XingGAN for Person Image Generation. CoRR abs/2007.09278 (2020) - [i127]Hao Tang, Song Bai, Philip H. S. Torr, Nicu Sebe:
Bipartite Graph Reasoning GANs for Person Image Generation. CoRR abs/2008.04381 (2020) - [i126]Harkirat Singh Behl, Atilim Günes Baydin, Ran Gal, Philip H. S. Torr, Vibhav Vineet:
AutoSimulate: (Quickly) Learning Synthetic Data Generation. CoRR abs/2008.08424 (2020) - [i125]Carlo Biffi, Steven McDonagh, Philip H. S. Torr, Ales Leonardis, Sarah Parisot:
Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection. CoRR abs/2008.09694 (2020) - [i124]Jonathon Luiten, Aljosa Osep, Patrick Dendorfer, Philip H. S. Torr, Andreas Geiger, Laura Leal-Taixé, Bastian Leibe:
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking. CoRR abs/2009.07736 (2020) - [i123]Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip H. S. Torr, Ales Leonardis, Gregory G. Slabaugh:
Diagnosing and Preventing Instabilities in Recurrent Video Processing. CoRR abs/2010.05099 (2020) - [i122]Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, Philip H. S. Torr:
Continual Learning in Low-rank Orthogonal Subspaces. CoRR abs/2010.11635 (2020) - [i121]Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz:
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation. CoRR abs/2010.12136 (2020) - [i120]Angira Sharma, Naeemullah Khan, Ganesh Sundaramoorthi, Philip H. S. Torr:
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation. CoRR abs/2010.14793 (2020) - [i119]Christian Schröder de Witt, Tarun Gupta, Denys Makoviichuk, Viktor Makoviychuk, Philip H. S. Torr, Mingfei Sun, Shimon Whiteson:
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? CoRR abs/2011.09533 (2020) - [i118]Shuyang Sun, Liang Chen, Gregory G. Slabaugh, Philip H. S. Torr:
Learning to Sample the Most Useful Training Patches from Images. CoRR abs/2011.12097 (2020) - [i117]Motasem Alfarra, Adel Bibi, Philip H. S. Torr, Bernard Ghanem:
Data Dependent Randomized Smoothing. CoRR abs/2012.04351 (2020) - [i116]Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip H. S. Torr, Raquel Urtasun, Jiaya Jia:
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation. CoRR abs/2012.06980 (2020) - [i115]Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip H. S. Torr, Vladlen Koltun:
Point Transformer. CoRR abs/2012.09164 (2020) - [i114]Xiaolong Liu, Yao Hu, Song Bai, Fei Ding, Xiang Bai, Philip H. S. Torr:
Multi-shot Temporal Event Localization: a Benchmark. CoRR abs/2012.09434 (2020) - [i113]Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr, Yarin Gal:
On Batch Normalisation for Approximate Bayesian Inference. CoRR abs/2012.13220 (2020) - [i112]Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H. S. Torr, Li Zhang:
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers. CoRR abs/2012.15840 (2020)
2010 – 2019
- 2019
- [j58]Ming-Ming Cheng, Yun Liu, Wen-Yan Lin, Ziming Zhang, Paul L. Rosin, Philip H. S. Torr:
BING: Binarized normed gradients for objectness estimation at 300fps. Comput. Vis. Media 5(1): 3-20 (2019) - [j57]Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu, Philip H. S. Torr:
Deeply Supervised Salient Object Detection with Short Connections. IEEE Trans. Pattern Anal. Mach. Intell. 41(4): 815-828 (2019) - [j56]Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan, Rudy Bunel, Mathieu Salzmann, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar:
Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials. SIAM J. Imaging Sci. 12(1): 287-318 (2019) - [j55]Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz, Alessio Tonioni, Thomas Joy, Luigi Di Stefano, Simon Walker, Philip H. S. Torr:
Real-Time Highly Accurate Dense Depth on a Power Budget Using an FPGA-CPU Hybrid SoC. IEEE Trans. Circuits Syst. II Express Briefs 66-II(5): 773-777 (2019) - [c207]Tommaso Cavallari, Luca Bertinetto, Jishnu Mukhoti, Philip H. S. Torr, Stuart Golodetz:
Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation. 3DV 2019: 564-573 - [c206]Mikayel Samvelyan, Tabish Rashid, Christian Schröder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob N. Foerster, Shimon Whiteson:
The StarCraft Multi-Agent Challenge. AAMAS 2019: 2186-2188 - [c205]Li Zhang, Xiangtai Li, Anurag Arnab, Kuiyuan Yang, Yunhai Tong, Philip H. S. Torr:
Dual Graph Convolutional Network for Semantic Segmentation. BMVC 2019: 254 - [c204]Feihu Zhang, Victor Adrian Prisacariu, Ruigang Yang, Philip H. S. Torr:
GA-Net: Guided Aggregation Net for End-To-End Stereo Matching. CVPR 2019: 185-194 - [c203]Song Bai, Peng Tang, Philip H. S. Torr, Longin Jan Latecki:
Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification. CVPR 2019: 740-749 - [c202]Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H. S. Torr:
Fast Online Object Tracking and Segmentation: A Unifying Approach. CVPR 2019: 1328-1338 - [c201]Eunwoo Kim, Chanho Ahn, Philip H. S. Torr, Songhwai Oh:
Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks. CVPR 2019: 2710-2719 - [c200]Alessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Learning to Adapt for Stereo. CVPR 2019: 9661-9670 - [c199]Adnane Boukhayma, Rodrigo Andrade de Bem, Philip H. S. Torr:
3D Hand Shape and Pose From Images in the Wild. CVPR 2019: 10843-10852 - [c198]Zhao Yang, Qiang Wang, Luca Bertinetto, Song Bai, Weiming Hu, Philip H. S. Torr:
Anchor Diffusion for Unsupervised Video Object Segmentation. ICCV 2019: 931-940 - [c197]Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman:
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation. ICCV 2019: 1171-1180 - [c196]Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley, Philip H. S. Torr:
Proximal Mean-Field for Neural Network Quantization. ICCV 2019: 4870-4879 - [c195]Jonathon Luiten, Philip H. S. Torr, Bastian Leibe:
Video Instance Segmentation 2019: A Winning Approach for Combined Detection, Segmentation, Classification and Tracking. ICCV Workshops 2019: 709-712 - [c194]Qiang Wang, Yi He, Xiaoyun Yang, Zhao Yang, Philip H. S. Torr:
An Empirical Study of Detection-Based Video Instance Segmentation. ICCV Workshops 2019: 713-716 - [c193]Matej Kristan, Amanda Berg, Linyu Zheng, Litu Rout, Luc Van Gool, Luca Bertinetto, Martin Danelljan, Matteo Dunnhofer, Meng Ni, Min Young Kim, Ming Tang, Ming-Hsuan Yang, Abdelrahman Eldesokey, Naveen Paluru, Niki Martinel, Pengfei Xu, Pengfei Zhang, Pengkun Zheng, Pengyu Zhang, Philip H. S. Torr, Qi Zhang, Qiang Wang, Qing Guo, Radu Timofte, Jani Käpylä, Rama Krishna Sai Subrahmanyam Gorthi, Richard M. Everson, Ruize Han, Ruohan Zhang, Shan You, Shao-Chuan Zhao, Shengwei Zhao, Shihu Li, Shikun Li, Shiming Ge, Gustavo Fernández, Shuai Bai, Shuosen Guan, Tengfei Xing, Tianyang Xu, Tianyu Yang, Ting Zhang, Tomás Vojír, Wei Feng, Weiming Hu, Weizhao Wang, Abel Gonzalez-Garcia, Wenjie Tang, Wenjun Zeng, Wenyu Liu, Xi Chen, Xi Qiu, Xiang Bai, Xiao-Jun Wu, Xiaoyun Yang, Xier Chen, Xin Li, Alireza Memarmoghadam, Xing Sun, Xingyu Chen, Xinmei Tian, Xu Tang, Xuefeng Zhu, Yan Huang, Yanan Chen, Yanchao Lian, Yang Gu, Yang Liu, Andong Lu, Yanjie Chen, Yi Zhang, Yinda Xu, Yingming Wang, Yingping Li, Yu Zhou, Yuan Dong, Yufei Xu, Yunhua Zhang, Yunkun Li, Anfeng He, Zeyu Wang, Zhao Luo, Zhaoliang Zhang, Zhenhua Feng, Zhenyu He, Zhichao Song, Zhihao Chen, Zhipeng Zhang, Zhirong Wu, Zhiwei Xiong, Zhongjian Huang, Anton Varfolomieiev, Zhu Teng, Zihan Ni, Antoni B. Chan, Jirí Matas, Ardhendu Shekhar Tripathi, Arnold W. M. Smeulders, Bala Suraj Pedasingu, Bao Xin Chen, Baopeng Zhang, Baoyuan Wu, Bi Li, Bin He, Bin Yan, Bing Bai, Ales Leonardis, Bing Li, Bo Li, Byeong Hak Kim, Chao Ma, Chen Fang, Chen Qian, Cheng Chen, Chenglong Li, Chengquan Zhang, Chi-Yi Tsai, Michael Felsberg, Chong Luo, Christian Micheloni, Chunhui Zhang, Dacheng Tao, Deepak Gupta, Dejia Song, Dong Wang, Efstratios Gavves, Eunu Yi, Fahad Shahbaz Khan, Roman P. Pflugfelder, Fangyi Zhang, Fei Wang, Fei Zhao, George De Ath, Goutam Bhat, Guangqi Chen, Guangting Wang, Guoxuan Li, Hakan Cevikalp, Hao Du, Joni-Kristian Kämäräinen, Haojie Zhao, Hasan Saribas, Ho Min Jung, Hongliang Bai, Hongyuan Yu, Houwen Peng, Huchuan Lu, Hui Li, Jiakun Li, Luka Cehovin Zajc, Jianhua Li, Jianlong Fu, Jie Chen, Jie Gao, Jie Zhao, Jin Tang, Jing Li, Jingjing Wu, Jingtuo Liu, Jinqiao Wang, Ondrej Drbohlav, Jinqing Qi, Jinyue Zhang, John K. Tsotsos, Jong Hyuk Lee, Joost van de Weijer, Josef Kittler, Jun Ha Lee, Junfei Zhuang, Kangkai Zhang, Kangkang Wang, Alan Lukezic, Kenan Dai, Lei Chen, Lei Liu, Leida Guo, Li Zhang, Liang Wang, Liangliang Wang, Lichao Zhang, Lijun Wang, Lijun Zhou:
The Seventh Visual Object Tracking VOT2019 Challenge Results. ICCV Workshops 2019: 2206-2241 - [c192]Luca Bertinetto, João F. Henriques, Philip H. S. Torr, Andrea Vedaldi:
Meta-learning with differentiable closed-form solvers. ICLR (Poster) 2019 - [c191]Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Snip: single-Shot Network Pruning based on Connection sensitivity. ICLR (Poster) 2019 - [c190]Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H. S. Torr, Nicolas Usunier:
Value Propagation Networks. ICLR (Poster) 2019 - [c189]Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr:
Controllable Text-to-Image Generation. NeurIPS 2019: 2063-2073 - [c188]Atilim Gunes Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Saeid Naderiparizi, Andreas Munk, Jialin Liu, Bradley Gram-Hansen, Gilles Louppe, Lawrence Meadows, Philip H. S. Torr, Victor W. Lee, Kyle Cranmer, Prabhat, Frank Wood:
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model. NeurIPS 2019: 5460-5473 - [c187]Christian Schröder de Witt, Jakob N. Foerster, Gregory Farquhar, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson:
Multi-Agent Common Knowledge Reinforcement Learning. NeurIPS 2019: 9924-9935 - [c186]Yuge Shi, Siddharth Narayanaswamy, Brooks Paige, Philip H. S. Torr:
Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models. NeurIPS 2019: 15692-15703 - [c185]Atilim Günes Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip H. S. Torr, Victor W. Lee, Kyle Cranmer, Prabhat, Frank Wood:
Etalumis: bringing probabilistic programming to scientific simulators at scale. SC 2019: 29:1-29:24 - [c184]Rodrigo Andrade de Bem, Arnab Ghosh, Adnane Boukhayma, Thalaiyasingam Ajanthan, N. Siddharth, Philip H. S. Torr:
A Conditional Deep Generative Model of People in Natural Images. WACV 2019: 1449-1458 - [i111]Song Bai, Feihu Zhang, Philip H. S. Torr:
Hypergraph Convolution and Hypergraph Attention. CoRR abs/1901.08150 (2019) - [i110]Song Bai, Yingwei Li, Yuyin Zhou, Qizhu Li, Philip H. S. Torr:
Adversarial Metric Attack for Person Re-identification. CoRR abs/1901.10650 (2019) - [i109]Adnane Boukhayma, Rodrigo Andrade de Bem, Philip H. S. Torr:
3D Hand Shape and Pose from Images in the Wild. CoRR abs/1902.03451 (2019) - [i108]Mikayel Samvelyan, Tabish Rashid, Christian Schröder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob N. Foerster, Shimon Whiteson:
The StarCraft Multi-Agent Challenge. CoRR abs/1902.04043 (2019) - [i107]Botos Csaba, Adnane Boukhayma, Viveka Kulharia, András Horváth, Philip H. S. Torr:
Domain Partitioning Network. CoRR abs/1902.08134 (2019) - [i106]Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Philip H. S. Torr, Marc'Aurelio Ranzato:
Continual Learning with Tiny Episodic Memories. CoRR abs/1902.10486 (2019) - [i105]Shanghua Gao, Ming-Ming Cheng, Kai Zhao, Xinyu Zhang, Ming-Hsuan Yang, Philip H. S. Torr:
Res2Net: A New Multi-scale Backbone Architecture. CoRR abs/1904.01169 (2019) - [i104]Alessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Learning to Adapt for Stereo. CoRR abs/1904.02957 (2019) - [i103]Eunwoo Kim, Chanho Ahn, Philip H. S. Torr, Songhwai Oh:
Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks. CoRR abs/1904.04562 (2019) - [i102]Feihu Zhang, Victor Adrian Prisacariu, Ruigang Yang, Philip H. S. Torr:
GA-Net: Guided Aggregation Net for End-to-end Stereo Matching. CoRR abs/1904.06587 (2019) - [i101]Harkirat Singh Behl, Atilim Günes Baydin, Philip H. S. Torr:
Alpha MAML: Adaptive Model-Agnostic Meta-Learning. CoRR abs/1905.07435 (2019) - [i100]Laurynas Miksys, Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr:
Straight to Shapes++: Real-time Instance Segmentation Made More Accurate. CoRR abs/1905.11358 (2019) - [i99]Bradley Gram-Hansen, Christian Schröder de Witt, Tom Rainforth, Philip H. S. Torr, Yee Whye Teh, Atilim Günes Baydin:
Hijacking Malaria Simulators with Probabilistic Programming. CoRR abs/1905.12432 (2019) - [i98]Amartya Sanyal, Philip H. S. Torr, Puneet K. Dokania:
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs. CoRR abs/1906.04659 (2019) - [i97]Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, Philip H. S. Torr:
A Signal Propagation Perspective for Pruning Neural Networks at Initialization. CoRR abs/1906.06307 (2019) - [i96]Tommaso Cavallari, Luca Bertinetto, Jishnu Mukhoti, Philip H. S. Torr, Stuart Golodetz:
Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation. CoRR abs/1906.08744 (2019) - [i95]Atilim Günes Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip H. S. Torr, Victor W. Lee, Kyle Cranmer, Prabhat, Frank Wood:
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale. CoRR abs/1907.03382 (2019) - [i94]Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz, Alessio Tonioni, Thomas Joy, Luigi Di Stefano, Simon Walker, Philip H. S. Torr:
Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC. CoRR abs/1907.07745 (2019) - [i93]Li Zhang, Dan Xu, Anurag Arnab, Philip H. S. Torr:
Dynamic Graph Message Passing Networks. CoRR abs/1908.06955 (2019) - [i92]Li Zhang, Xiangtai Li, Anurag Arnab, Kuiyuan Yang, Yunhai Tong, Philip H. S. Torr:
Dual Graph Convolutional Network for Semantic Segmentation. CoRR abs/1909.06121 (2019) - [i91]Rudy Bunel, Jingyue Lu, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, M. Pawan Kumar:
Branch and Bound for Piecewise Linear Neural Network Verification. CoRR abs/1909.06588 (2019) - [i90]Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr:
Controllable Text-to-Image Generation. CoRR abs/1909.07083 (2019) - [i89]Arnab Ghosh, Richard Zhang, Puneet K. Dokania, Oliver Wang, Alexei A. Efros, Philip H. S. Torr, Eli Shechtman:
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation. CoRR abs/1909.11081 (2019) - [i88]Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr, Richard Hartley, Puneet K. Dokania:
Mirror Descent View for Neural Network Quantization. CoRR abs/1910.08237 (2019) - [i87]Saeid Naderiparizi, Adam Scibior, Andreas Munk, Mehrdad Ghadiri, Atilim Günes Baydin, Bradley Gram-Hansen, Christian Schröder de Witt, Robert Zinkov, Philip H. S. Torr, Tom Rainforth, Yee Whye Teh, Frank Wood:
Amortized Rejection Sampling in Universal Probabilistic Programming. CoRR abs/1910.09056 (2019) - [i86]Zhao Yang, Qiang Wang, Luca Bertinetto, Weiming Hu, Song Bai, Philip H. S. Torr:
Anchor Diffusion for Unsupervised Video Object Segmentation. CoRR abs/1910.10895 (2019) - [i85]Yuge Shi, N. Siddharth, Brooks Paige, Philip H. S. Torr:
Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models. CoRR abs/1911.03393 (2019) - [i84]Hao Tang, Hong Liu, Dan Xu, Philip H. S. Torr, Nicu Sebe:
AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks. CoRR abs/1911.11897 (2019) - [i83]Paul Voigtlaender, Jonathon Luiten, Philip H. S. Torr, Bastian Leibe:
Siam R-CNN: Visual Tracking by Re-Detection. CoRR abs/1911.12836 (2019) - [i82]Andrew Gambardella, Atilim Günes Baydin, Philip H. S. Torr:
Transflow Learning: Repurposing Flow Models Without Retraining. CoRR abs/1911.13270 (2019) - [i81]Feihu Zhang, Xiaojuan Qi, Ruigang Yang, Victor Prisacariu, Benjamin W. Wah, Philip H. S. Torr:
Domain-invariant Stereo Matching Networks. CoRR abs/1911.13287 (2019) - [i80]Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr:
ManiGAN: Text-Guided Image Manipulation. CoRR abs/1912.06203 (2019) - [i79]Alexander Muryy, N. Siddharth, Nantas Nardelli, Andrew Glennerster, Philip H. S. Torr:
Lessons from reinforcement learning for biological representations of space. CoRR abs/1912.06615 (2019) - [i78]Nan Xue, Song Bai, Fudong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang, Philip H. S. Torr:
Learning Regional Attraction for Line Segment Detection. CoRR abs/1912.09344 (2019) - [i77]Hao Tang, Dan Xu, Yan Yan, Philip H. S. Torr, Nicu Sebe:
Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation. CoRR abs/1912.12215 (2019) - 2018
- [j54]Wen-Yan Lin, Fan Wang, Ming-Ming Cheng, Sai-Kit Yeung, Philip H. S. Torr, Minh N. Do, Jiangbo Lu:
CODE: Coherence Based Decision Boundaries for Feature Correspondence. IEEE Trans. Pattern Anal. Mach. Intell. 40(1): 34-47 (2018) - [j53]Ziming Zhang, Yun Liu, Xi Chen, Yanjun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, Philip H. S. Torr:
Sequential Optimization for Efficient High-Quality Object Proposal Generation. IEEE Trans. Pattern Anal. Mach. Intell. 40(5): 1209-1223 (2018) - [j52]Oscar Rahnama, Duncan P. Frost, Ondrej Miksik, Philip H. S. Torr:
Real-Time Dense Stereo Matching With ELAS on FPGA-Accelerated Embedded Devices. IEEE Robotics Autom. Lett. 3(3): 2008-2015 (2018) - [j51]Måns Larsson, Anurag Arnab, Shuai Zheng, Philip H. S. Torr, Fredrik Kahl:
Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference. SIAM J. Imaging Sci. 11(4): 2610-2628 (2018) - [j50]Anurag Arnab, Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Måns Larsson, Alexander Kirillov, Bogdan Savchynskyy, Carsten Rother, Fredrik Kahl, Philip H. S. Torr:
Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction. IEEE Signal Process. Mag. 35(1): 37-52 (2018) - [j49]Stuart Golodetz, Tommaso Cavallari, Nicholas A. Lord, Victor Adrian Prisacariu, David William Murray, Philip H. S. Torr:
Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation. IEEE Trans. Vis. Comput. Graph. 24(11): 2895-2905 (2018) - [c183]Rodrigo Andrade de Bem, Anurag Arnab, Stuart Golodetz, Michael Sapienza, Philip H. S. Torr:
Deep Fully-Connected Part-Based Models for Human Pose Estimation. ACML 2018: 327-342 - [c182]Harkirat S. Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr:
Incremental Tube Construction for Human Action Detection. BMVC 2018: 60 - [c181]Anurag Arnab, Ondrej Miksik, Philip H. S. Torr:
On the Robustness of Semantic Segmentation Models to Adversarial Attacks. CVPR 2018: 888-897 - [c180]Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, Timothy M. Hospedales:
Learning to Compare: Relation Network for Few-Shot Learning. CVPR 2018: 1199-1208 - [c179]Daniela Massiceti, N. Siddharth, Puneet Kumar Dokania, Philip H. S. Torr:
FlipDial: A Generative Model for Two-Way Visual Dialogue. CVPR 2018: 6097-6105 - [c178]Arnab Ghosh, Viveka Kulharia, Vinay P. Namboodiri, Philip H. S. Torr, Puneet Kumar Dokania:
Multi-Agent Diverse Generative Adversarial Networks. CVPR 2018: 8513-8521 - [c177]Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Luka Cehovin Zajc, Tomás Vojír, Goutam Bhat, Alan Lukezic, Abdelrahman Eldesokey, Gustavo Fernández, Álvaro García-Martín, Álvaro Iglesias-Arias, A. Aydin Alatan, Abel González-García, Alfredo Petrosino, Alireza Memarmoghadam, Andrea Vedaldi, Andrej Muhic, Anfeng He, Arnold W. M. Smeulders, Asanka G. Perera, Bo Li, Boyu Chen, Changick Kim, Changsheng Xu, Changzhen Xiong, Cheng Tian, Chong Luo, Chong Sun, Cong Hao, Daijin Kim, Deepak Mishra, Deming Chen, Dong Wang, Dongyoon Wee, Efstratios Gavves, Erhan Gundogdu, Erik Velasco-Salido, Fahad Shahbaz Khan, Fan Yang, Fei Zhao, Feng Li, Francesco Battistone, George De Ath, Gorthi R. K. Sai Subrahmanyam, Guilherme Sousa Bastos, Haibin Ling, Hamed Kiani Galoogahi, Hankyeol Lee, Haojie Li, Haojie Zhao, Heng Fan, Honggang Zhang, Horst Possegger, Houqiang Li, Huchuan Lu, Hui Zhi, Huiyun Li, Hyemin Lee, Hyung Jin Chang, Isabela Drummond, Jack Valmadre, Jaime Spencer Martin, Javaan Singh Chahl, Jin Young Choi, Jing Li, Jinqiao Wang, Jinqing Qi, Jinyoung Sung, Joakim Johnander, João F. Henriques, Jongwon Choi, Joost van de Weijer, Jorge Rodríguez Herranz, José M. Martínez, Josef Kittler, Junfei Zhuang, Junyu Gao, Klemen Grm, Lichao Zhang, Lijun Wang, Lingxiao Yang, Litu Rout, Liu Si, Luca Bertinetto, Lutao Chu, Manqiang Che, Mario Edoardo Maresca, Martin Danelljan, Ming-Hsuan Yang, Mohamed H. Abdelpakey, Mohamed S. Shehata, Myunggu Kang, Namhoon Lee, Ning Wang, Ondrej Miksik, Payman Moallem, Pablo Vicente-Moñivar, Pedro Senna, Peixia Li, Philip H. S. Torr, Priya Mariam Raju, Ruihe Qian, Qiang Wang, Qin Zhou, Qing Guo, Rafael Martin Nieto, Rama Krishna Sai Subrahmanyam Gorthi, Ran Tao, Richard Bowden, Richard M. Everson, Runling Wang, Sangdoo Yun, Seokeon Choi, Sergio Vivas, Shuai Bai, Shuangping Huang, Sihang Wu, Simon Hadfield, Siwen Wang, Stuart Golodetz, Ming Tang, Tianyang Xu, Tianzhu Zhang, Tobias Fischer, Vincenzo Santopietro, Vitomir Struc, Wei Wang, Wangmeng Zuo, Wei Feng, Wei Wu, Wei Zou, Weiming Hu, Wengang Zhou, Wenjun Zeng, Xiaofan Zhang, Xiaohe Wu, Xiao-Jun Wu, Xinmei Tian, Yan Li, Yan Lu, Yee Wei Law, Yi Wu, Yiannis Demiris, Yicai Yang, Yifan Jiao, Yuhong Li, Yunhua Zhang, Yuxuan Sun, Zheng Zhang, Zheng Zhu, Zhenhua Feng, Zhihui Wang, Zhiqun He:
The Sixth Visual Object Tracking VOT2018 Challenge Results. ECCV Workshops (1) 2018: 3-53 - [c176]Qizhu Li, Anurag Arnab, Philip H. S. Torr:
Weakly- and Semi-supervised Panoptic Segmentation. ECCV (15) 2018: 106-124 - [c175]Rodrigo Andrade de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, N. Siddharth, Philip H. S. Torr:
A Semi-supervised Deep Generative Model for Human Body Analysis. ECCV Workshops (2) 2018: 500-517 - [c174]Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. ECCV (11) 2018: 556-572 - [c173]Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr:
Devon: Deformable Volume Network for Learning Optical Flow. ECCV Workshops (6) 2018: 673-677 - [c172]Jack Valmadre, Luca Bertinetto, João F. Henriques, Ran Tao, Andrea Vedaldi, Arnold W. M. Smeulders, Philip H. S. Torr, Efstratios Gavves:
Long-Term Tracking in the Wild: A Benchmark. ECCV (3) 2018: 692-707 - [c171]Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz, Simon Walker, Philip H. S. Torr:
R3SGM: Real-Time Raster-Respecting Semi-Global Matching for Power-Constrained Systems. FPT 2018: 102-109 - [c170]Saumya Jetley, Nicholas A. Lord, Namhoon Lee, Philip H. S. Torr:
Learn to Pay Attention. ICLR (Poster) 2018 - [c169]Stuart Golodetz, Tommaso Cavallari, Nicholas A. Lord, Victor Adrian Prisacariu, David William Murray, Philip H. S. Torr:
Live Collaborative Large-Scale Dense 3D Reconstruction Using Consumer-Grade Hardware. ISMAR Adjunct 2018: 413-414 - [c168]Rudy Bunel, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, Pawan Kumar Mudigonda:
A Unified View of Piecewise Linear Neural Network Verification. NeurIPS 2018: 4795-4804 - [c167]Saumya Jetley, Nicholas A. Lord, Philip H. S. Torr:
With Friends Like These, Who Needs Adversaries? NeurIPS 2018: 10772-10782 - [i76]Stuart Golodetz, Tommaso Cavallari, Nicholas A. Lord, Victor Adrian Prisacariu, David William Murray, Philip H. S. Torr:
Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation. CoRR abs/1801.08361 (2018) - [i75]Arslan Chaudhry, Puneet Kumar Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr:
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence. CoRR abs/1801.10112 (2018) - [i74]Daniela Massiceti, N. Siddharth, Puneet Kumar Dokania, Philip H. S. Torr:
FlipDial: A Generative Model for Two-Way Visual Dialogue. CoRR abs/1802.03803 (2018) - [i73]Oscar Rahnama, Duncan P. Frost, Ondrej Miksik, Philip H. S. Torr:
Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices. CoRR abs/1802.07210 (2018) - [i72]Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr:
Devon: Deformable Volume Network for Learning Optical Flow. CoRR abs/1802.07351 (2018) - [i71]Jack Valmadre, Luca Bertinetto, João F. Henriques, Ran Tao, Andrea Vedaldi, Arnold W. M. Smeulders, Philip H. S. Torr, Efstratios Gavves:
Long-term Tracking in the Wild: A Benchmark. CoRR abs/1803.09502 (2018) - [i70]Qibin Hou, Ming-Ming Cheng, Jiang-Jiang Liu, Philip H. S. Torr:
WebSeg: Learning Semantic Segmentation from Web Searches. CoRR abs/1803.09859 (2018) - [i69]Qibin Hou, Jiang-Jiang Liu, Ming-Ming Cheng, Ali Borji, Philip H. S. Torr:
Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction. CoRR abs/1803.09860 (2018) - [i68]Saumya Jetley, Nicholas A. Lord, Namhoon Lee, Philip H. S. Torr:
Learn To Pay Attention. CoRR abs/1804.02391 (2018) - [i67]Rodrigo Andrade de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, N. Siddharth, Philip H. S. Torr:
DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis. CoRR abs/1804.06364 (2018) - [i66]Amartya Sanyal, Varun Kanade, Philip H. S. Torr:
Low Rank Structure of Learned Representations. CoRR abs/1804.07090 (2018) - [i65]Luca Bertinetto, João F. Henriques, Philip H. S. Torr, Andrea Vedaldi:
Meta-learning with differentiable closed-form solvers. CoRR abs/1805.08136 (2018) - [i64]Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan, Rudy Bunel, Mathieu Salzmann, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar:
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials. CoRR abs/1805.09028 (2018) - [i63]Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H. S. Torr, Nicolas Usunier:
Value Propagation Networks. CoRR abs/1805.11199 (2018) - [i62]Saumya Jetley, Nicholas A. Lord, Philip H. S. Torr:
With Friends Like These, Who Needs Adversaries? CoRR abs/1807.04200 (2018) - [i61]Qizhu Li, Anurag Arnab, Philip H. S. Torr:
Weakly- and Semi-Supervised Panoptic Segmentation. CoRR abs/1808.03575 (2018) - [i60]Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr:
SNIP: Single-shot Network Pruning based on Connection Sensitivity. CoRR abs/1810.02340 (2018) - [i59]Jakob N. Foerster, Christian A. Schröder de Witt, Gregory Farquhar, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson:
Multi-Agent Common Knowledge Reinforcement Learning. CoRR abs/1810.11702 (2018) - [i58]Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord, Julien P. C. Valentin, Victor Adrian Prisacariu, Luigi Di Stefano, Philip H. S. Torr:
Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade. CoRR abs/1810.12163 (2018) - [i57]Oscar Rahnama, Tommaso Cavallari, Stuart Golodetz, Simon Walker, Philip H. S. Torr:
R$^3$SGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems. CoRR abs/1810.12988 (2018) - [i56]Tian Xu, Jiayu Zhan, Oliver G. B. Garrod, Philip H. S. Torr, Song-Chun Zhu, Robin A. A. Ince, Philippe G. Schyns:
Deeper Interpretability of Deep Networks. CoRR abs/1811.07807 (2018) - [i55]Harkirat Singh Behl, Mohammad Najafi, Philip H. S. Torr:
Meta Learning Deep Visual Words for Fast Video Object Segmentation. CoRR abs/1812.01397 (2018) - [i54]Thalaiyasingam Ajanthan, Puneet Kumar Dokania, Richard I. Hartley, Philip H. S. Torr:
Proximal Mean-field for Neural Network Quantization. CoRR abs/1812.04353 (2018) - [i53]Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H. S. Torr:
Fast Online Object Tracking and Segmentation: A Unifying Approach. CoRR abs/1812.05050 (2018) - [i52]Daniela Massiceti, Puneet K. Dokania, N. Siddharth, Philip H. S. Torr:
Visual Dialogue without Vision or Dialogue. CoRR abs/1812.06417 (2018) - [i51]Zhao Yang, Song Bai, Li Zhang, Philip H. S. Torr:
Learn to Interpret Atari Agents. CoRR abs/1812.11276 (2018) - 2017
- [j48]Srikumar Ramalingam, Chris Russell, Lubor Ladicky, Philip H. S. Torr:
Efficient minimization of higher order submodular functions using monotonic Boolean functions. Discret. Appl. Math. 220: 1-19 (2017) - [j47]Peng Wang, Chunhua Shen, Anton van den Hengel, Philip H. S. Torr:
Large-Scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications. IEEE Trans. Pattern Anal. Mach. Intell. 39(3): 470-485 (2017) - [c166]Jack Hunt, Victor Adrian Prisacariu, Stuart Golodetz, Tommaso Cavallari, Nicholas A. Lord, Philip H. S. Torr:
Probabilistic Object Reconstruction with Online Global Model Correction. 3DV 2017: 291-300 - [c165]Arslan Chaudhry, Puneet Kumar Dokania, Philip H. S. Torr:
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. BMVC 2017 - [c164]Qizhu Li, Anurag Arnab, Philip H. S. Torr:
Holistic, Instance-level Human Parsing. BMVC 2017 - [c163]Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord, Julien P. C. Valentin, Luigi Di Stefano, Philip H. S. Torr:
On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation. CVPR 2017: 218-227 - [c162]Anurag Arnab, Philip H. S. Torr:
Pixelwise Instance Segmentation with a Dynamically Instantiated Network. CVPR 2017: 879-888 - [c161]Namhoon Lee, Wongun Choi, Paul Vernaza, Christopher B. Choy, Philip H. S. Torr, Manmohan Chandraker:
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents. CVPR 2017: 2165-2174 - [c160]Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel, Mathieu Salzmann, Philip H. S. Torr, M. Pawan Kumar:
Efficient Linear Programming for Dense CRFs. CVPR 2017: 2934-2942 - [c159]Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr:
Straight to Shapes: Real-Time Detection of Encoded Shapes. CVPR 2017: 4207-4216 - [c158]Jack Valmadre, Luca Bertinetto, João F. Henriques, Andrea Vedaldi, Philip H. S. Torr:
End-to-End Representation Learning for Correlation Filter Based Tracking. CVPR 2017: 5000-5008 - [c157]