BibTeX records: Wei Han 0002

download as .bib file

@article{DBLP:journals/corr/abs-2402-01828,
  author       = {Mingqiu Wang and
                  Izhak Shafran and
                  Hagen Soltau and
                  Wei Han and
                  Yuan Cao and
                  Dian Yu and
                  Laurent El Shafey},
  title        = {Retrieval Augmented End-to-End Spoken Dialog Models},
  journal      = {CoRR},
  volume       = {abs/2402.01828},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.01828},
  doi          = {10.48550/ARXIV.2402.01828},
  eprinttype    = {arXiv},
  eprint       = {2402.01828},
  timestamp    = {Fri, 09 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-01828.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiHHBPSSZHSB23,
  author       = {Bo Li and
                  Dongseong Hwang and
                  Zhouyuan Huo and
                  Junwen Bai and
                  Guru Prakash and
                  Tara N. Sainath and
                  Khe Chai Sim and
                  Yu Zhang and
                  Wei Han and
                  Trevor Strohman and
                  Fran{\c{c}}oise Beaufays},
  title        = {Efficient Domain Adaptation for Speech Foundation Models},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10096330},
  doi          = {10.1109/ICASSP49357.2023.10096330},
  timestamp    = {Sun, 05 Nov 2023 16:51:21 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/LiHHBPSSZHSB23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangCZZHH23,
  author       = {Yongqiang Wang and
                  Zhehuai Chen and
                  Chengjian Zheng and
                  Yu Zhang and
                  Wei Han and
                  Parisa Haghani},
  title        = {Accelerating {RNN-T} Training and Inference Using {CTC} Guidance},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10096065},
  doi          = {10.1109/ICASSP49357.2023.10096065},
  timestamp    = {Sun, 05 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/WangCZZHH23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-01496,
  author       = {Bo Li and
                  Dongseong Hwang and
                  Zhouyuan Huo and
                  Junwen Bai and
                  Guru Prakash and
                  Tara N. Sainath and
                  Khe Chai Sim and
                  Yu Zhang and
                  Wei Han and
                  Trevor Strohman and
                  Fran{\c{c}}oise Beaufays},
  title        = {Efficient Domain Adaptation for Speech Foundation Models},
  journal      = {CoRR},
  volume       = {abs/2302.01496},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2302.01496},
  doi          = {10.48550/ARXIV.2302.01496},
  eprinttype    = {arXiv},
  eprint       = {2302.01496},
  timestamp    = {Fri, 24 Feb 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-01496.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-01037,
  author       = {Yu Zhang and
                  Wei Han and
                  James Qin and
                  Yongqiang Wang and
                  Ankur Bapna and
                  Zhehuai Chen and
                  Nanxin Chen and
                  Bo Li and
                  Vera Axelrod and
                  Gary Wang and
                  Zhong Meng and
                  Ke Hu and
                  Andrew Rosenberg and
                  Rohit Prabhavalkar and
                  Daniel S. Park and
                  Parisa Haghani and
                  Jason Riesa and
                  Ginger Perng and
                  Hagen Soltau and
                  Trevor Strohman and
                  Bhuvana Ramabhadran and
                  Tara N. Sainath and
                  Pedro J. Moreno and
                  Chung{-}Cheng Chiu and
                  Johan Schalkwyk and
                  Fran{\c{c}}oise Beaufays and
                  Yonghui Wu},
  title        = {Google {USM:} Scaling Automatic Speech Recognition Beyond 100 Languages},
  journal      = {CoRR},
  volume       = {abs/2303.01037},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2303.01037},
  doi          = {10.48550/ARXIV.2303.01037},
  eprinttype    = {arXiv},
  eprint       = {2303.01037},
  timestamp    = {Tue, 07 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2303-01037.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-04374,
  author       = {Shikhar Vashishth and
                  Shikhar Bharadwaj and
                  Sriram Ganapathy and
                  Ankur Bapna and
                  Min Ma and
                  Wei Han and
                  Vera Axelrod and
                  Partha Talukdar},
  title        = {Label Aware Speech Representation Learning For Language Identification},
  journal      = {CoRR},
  volume       = {abs/2306.04374},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.04374},
  doi          = {10.48550/ARXIV.2306.04374},
  eprinttype    = {arXiv},
  eprint       = {2306.04374},
  timestamp    = {Tue, 13 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-04374.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-07944,
  author       = {Mingqiu Wang and
                  Izhak Shafran and
                  Hagen Soltau and
                  Wei Han and
                  Yuan Cao and
                  Dian Yu and
                  Laurent El Shafey},
  title        = {Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs
                  for Speech Understanding},
  journal      = {CoRR},
  volume       = {abs/2306.07944},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.07944},
  doi          = {10.48550/ARXIV.2306.07944},
  eprinttype    = {arXiv},
  eprint       = {2306.07944},
  timestamp    = {Mon, 19 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-07944.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-00899,
  author       = {Pierre Sermanet and
                  Tianli Ding and
                  Jeffrey Zhao and
                  Fei Xia and
                  Debidatta Dwibedi and
                  Keerthana Gopalakrishnan and
                  Christine Chan and
                  Gabriel Dulac{-}Arnold and
                  Sharath Maddineni and
                  Nikhil J. Joshi and
                  Pete Florence and
                  Wei Han and
                  Robert Baruch and
                  Yao Lu and
                  Suvir Mirchandani and
                  Peng Xu and
                  Pannag Sanketi and
                  Karol Hausman and
                  Izhak Shafran and
                  Brian Ichter and
                  Yuan Cao},
  title        = {RoboVQA: Multimodal Long-Horizon Reasoning for Robotics},
  journal      = {CoRR},
  volume       = {abs/2311.00899},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2311.00899},
  doi          = {10.48550/ARXIV.2311.00899},
  eprinttype    = {arXiv},
  eprint       = {2311.00899},
  timestamp    = {Mon, 11 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2311-00899.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jstsp/ZhangPHQGSJXHWZ22,
  author       = {Yu Zhang and
                  Daniel S. Park and
                  Wei Han and
                  James Qin and
                  Anmol Gulati and
                  Joel Shor and
                  Aren Jansen and
                  Yuanzhong Xu and
                  Yanping Huang and
                  Shibo Wang and
                  Zongwei Zhou and
                  Bo Li and
                  Min Ma and
                  William Chan and
                  Jiahui Yu and
                  Yongqiang Wang and
                  Liangliang Cao and
                  Khe Chai Sim and
                  Bhuvana Ramabhadran and
                  Tara N. Sainath and
                  Fran{\c{c}}oise Beaufays and
                  Zhifeng Chen and
                  Quoc V. Le and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning
                  for Automatic Speech Recognition},
  journal      = {{IEEE} J. Sel. Top. Signal Process.},
  volume       = {16},
  number       = {6},
  pages        = {1519--1532},
  year         = {2022},
  url          = {https://doi.org/10.1109/JSTSP.2022.3182537},
  doi          = {10.1109/JSTSP.2022.3182537},
  timestamp    = {Sun, 13 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/jstsp/ZhangPHQGSJXHWZ22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ShorJHPZ22,
  author       = {Joel Shor and
                  Aren Jansen and
                  Wei Han and
                  Daniel S. Park and
                  Yu Zhang},
  title        = {Universal Paralinguistic Speech Representations Using self-Supervised
                  Conformers},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  pages        = {3169--3173},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICASSP43922.2022.9747197},
  doi          = {10.1109/ICASSP43922.2022.9747197},
  timestamp    = {Tue, 07 Jun 2022 17:34:47 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/ShorJHPZ22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SainathHNBWQCPG22,
  author       = {Tara N. Sainath and
                  Yanzhang He and
                  Arun Narayanan and
                  Rami Botros and
                  Weiran Wang and
                  David Qiu and
                  Chung{-}Cheng Chiu and
                  Rohit Prabhavalkar and
                  Alexander Gruenstein and
                  Anmol Gulati and
                  Bo Li and
                  David Rybach and
                  Emmanuel Guzman and
                  Ian McGraw and
                  James Qin and
                  Krzysztof Choromanski and
                  Qiao Liang and
                  Robert David and
                  Ruoming Pang and
                  Shuo{-}Yiin Chang and
                  Trevor Strohman and
                  W. Ronny Huang and
                  Wei Han and
                  Yonghui Wu and
                  Yu Zhang},
  title        = {Improving The Latency And Quality Of Cascaded Encoders},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  pages        = {8112--8116},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICASSP43922.2022.9747879},
  doi          = {10.1109/ICASSP43922.2022.9747879},
  timestamp    = {Tue, 07 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/SainathHNBWQCPG22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-08014,
  author       = {Al{\"{e}}na Aks{\"{e}}nova and
                  Zhehuai Chen and
                  Chung{-}Cheng Chiu and
                  Daan van Esch and
                  Pavel Golik and
                  Wei Han and
                  Levi King and
                  Bhuvana Ramabhadran and
                  Andrew Rosenberg and
                  Suzan Schwartz and
                  Gary Wang},
  title        = {Accented Speech Recognition: Benchmarking, Pre-training, and Diverse
                  Data},
  journal      = {CoRR},
  volume       = {abs/2205.08014},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2205.08014},
  doi          = {10.48550/ARXIV.2205.08014},
  eprinttype    = {arXiv},
  eprint       = {2205.08014},
  timestamp    = {Tue, 24 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2205-08014.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-08704,
  author       = {Hagen Soltau and
                  Izhak Shafran and
                  Mingqiu Wang and
                  Abhinav Rastogi and
                  Jeffrey Zhao and
                  Ye Jia and
                  Wei Han and
                  Yuan Cao and
                  Aramys Miranda},
  title        = {Speech Aware Dialog System Technology Challenge {(DSTC11)}},
  journal      = {CoRR},
  volume       = {abs/2212.08704},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.08704},
  doi          = {10.48550/ARXIV.2212.08704},
  eprinttype    = {arXiv},
  eprint       = {2212.08704},
  timestamp    = {Tue, 28 Feb 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-08704.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ChungZHCQPW21,
  author       = {Yu{-}An Chung and
                  Yu Zhang and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  James Qin and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {w2v-BERT: Combining Contrastive Learning and Masked Language Modeling
                  for Self-Supervised Speech Pre-Training},
  booktitle    = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
                  2021, Cartagena, Colombia, December 13-17, 2021},
  pages        = {244--250},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ASRU51503.2021.9688253},
  doi          = {10.1109/ASRU51503.2021.9688253},
  timestamp    = {Wed, 09 Feb 2022 09:03:03 +0100},
  biburl       = {https://dblp.org/rec/conf/asru/ChungZHCQPW21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiGYSCNCPHQ0LZS21,
  author       = {Bo Li and
                  Anmol Gulati and
                  Jiahui Yu and
                  Tara N. Sainath and
                  Chung{-}Cheng Chiu and
                  Arun Narayanan and
                  Shuo{-}Yiin Chang and
                  Ruoming Pang and
                  Yanzhang He and
                  James Qin and
                  Wei Han and
                  Qiao Liang and
                  Yu Zhang and
                  Trevor Strohman and
                  Yonghui Wu},
  title        = {A Better and Faster end-to-end Model for Streaming {ASR}},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {5634--5638},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9413899},
  doi          = {10.1109/ICASSP39728.2021.9413899},
  timestamp    = {Tue, 07 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/LiGYSCNCPHQ0LZS21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YuCLCSHNHGWP21,
  author       = {Jiahui Yu and
                  Chung{-}Cheng Chiu and
                  Bo Li and
                  Shuo{-}Yiin Chang and
                  Tara N. Sainath and
                  Yanzhang He and
                  Arun Narayanan and
                  Wei Han and
                  Anmol Gulati and
                  Yonghui Wu and
                  Ruoming Pang},
  title        = {FastEmit: Low-Latency Streaming {ASR} with Sequence-Level Emission
                  Regularization},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {6004--6008},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9413803},
  doi          = {10.1109/ICASSP39728.2021.9413803},
  timestamp    = {Mon, 12 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/YuCLCSHNHGWP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/DoutreHMLCPNMZC21,
  author       = {Thibault Doutre and
                  Wei Han and
                  Min Ma and
                  Zhiyun Lu and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Arun Narayanan and
                  Ananya Misra and
                  Yu Zhang and
                  Liangliang Cao},
  title        = {Improving Streaming Automatic Speech Recognition with Non-Streaming
                  Model Distillation on Unsupervised Data},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {6558--6562},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9413692},
  doi          = {10.1109/ICASSP39728.2021.9413692},
  timestamp    = {Mon, 15 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/DoutreHMLCPNMZC21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/YuHGCLSWP21,
  author       = {Jiahui Yu and
                  Wei Han and
                  Anmol Gulati and
                  Chung{-}Cheng Chiu and
                  Bo Li and
                  Tara N. Sainath and
                  Yonghui Wu and
                  Ruoming Pang},
  title        = {Dual-mode {ASR:} Unify and Improve Streaming {ASR} with Full-context
                  Modeling},
  booktitle    = {9th International Conference on Learning Representations, {ICLR} 2021,
                  Virtual Event, Austria, May 3-7, 2021},
  publisher    = {OpenReview.net},
  year         = {2021},
  url          = {https://openreview.net/forum?id=Pz\_dcqfcKW8},
  timestamp    = {Mon, 12 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/YuHGCLSWP21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/DoutreHCPSC21,
  author       = {Thibault Doutre and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Olivier Siohan and
                  Liangliang Cao},
  editor       = {Hynek Hermansky and
                  Honza Cernock{\'{y}} and
                  Luk{\'{a}}s Burget and
                  Lori Lamel and
                  Odette Scharenborg and
                  Petr Motl{\'{\i}}cek},
  title        = {Bridging the Gap Between Streaming and Non-Streaming {ASR} Systems
                  by Distilling Ensembles of {CTC} and {RNN-T} Models},
  booktitle    = {Interspeech 2021, 22nd Annual Conference of the International Speech
                  Communication Association, Brno, Czechia, 30 August - 3 September
                  2021},
  pages        = {1807--1811},
  publisher    = {{ISCA}},
  year         = {2021},
  url          = {https://doi.org/10.21437/Interspeech.2021-637},
  doi          = {10.21437/INTERSPEECH.2021-637},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/DoutreHCPSC21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/ChiuNHPZJPSNCW21,
  author       = {Chung{-}Cheng Chiu and
                  Arun Narayanan and
                  Wei Han and
                  Rohit Prabhavalkar and
                  Yu Zhang and
                  Navdeep Jaitly and
                  Ruoming Pang and
                  Tara N. Sainath and
                  Patrick Nguyen and
                  Liangliang Cao and
                  Yonghui Wu},
  title        = {{RNN-T} Models Fail to Generalize to Out-of-Domain Audio: Causes and
                  Solutions},
  booktitle    = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
                  China, January 19-22, 2021},
  pages        = {873--880},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/SLT48900.2021.9383518},
  doi          = {10.1109/SLT48900.2021.9383518},
  timestamp    = {Fri, 07 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/slt/ChiuNHPZJPSNCW21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02757,
  author       = {Zhiyun Lu and
                  Wei Han and
                  Yu Zhang and
                  Liangliang Cao},
  title        = {Exploring Targeted Universal Adversarial Perturbations to End-to-end
                  {ASR} Models},
  journal      = {CoRR},
  volume       = {abs/2104.02757},
  year         = {2021},
  url          = {https://arxiv.org/abs/2104.02757},
  eprinttype    = {arXiv},
  eprint       = {2104.02757},
  timestamp    = {Fri, 07 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2104-02757.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-14346,
  author       = {Thibault Doutre and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Olivier Siohan and
                  Liangliang Cao},
  title        = {Bridging the gap between streaming and non-streaming {ASR} systems
                  bydistilling ensembles of {CTC} and {RNN-T} models},
  journal      = {CoRR},
  volume       = {abs/2104.14346},
  year         = {2021},
  url          = {https://arxiv.org/abs/2104.14346},
  eprinttype    = {arXiv},
  eprint       = {2104.14346},
  timestamp    = {Tue, 04 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2104-14346.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-06209,
  author       = {Yu{-}An Chung and
                  Yu Zhang and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  James Qin and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {W2v-BERT: Combining Contrastive Learning and Masked Language Modeling
                  for Self-Supervised Speech Pre-Training},
  journal      = {CoRR},
  volume       = {abs/2108.06209},
  year         = {2021},
  url          = {https://arxiv.org/abs/2108.06209},
  eprinttype    = {arXiv},
  eprint       = {2108.06209},
  timestamp    = {Mon, 23 May 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2108-06209.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-13226,
  author       = {Yu Zhang and
                  Daniel S. Park and
                  Wei Han and
                  James Qin and
                  Anmol Gulati and
                  Joel Shor and
                  Aren Jansen and
                  Yuanzhong Xu and
                  Yanping Huang and
                  Shibo Wang and
                  Zongwei Zhou and
                  Bo Li and
                  Min Ma and
                  William Chan and
                  Jiahui Yu and
                  Yongqiang Wang and
                  Liangliang Cao and
                  Khe Chai Sim and
                  Bhuvana Ramabhadran and
                  Tara N. Sainath and
                  Fran{\c{c}}oise Beaufays and
                  Zhifeng Chen and
                  Quoc V. Le and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning
                  for Automatic Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2109.13226},
  year         = {2021},
  url          = {https://arxiv.org/abs/2109.13226},
  eprinttype    = {arXiv},
  eprint       = {2109.13226},
  timestamp    = {Wed, 20 Jul 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2109-13226.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/SunKDCPTGZCCVHN20,
  author       = {Pei Sun and
                  Henrik Kretzschmar and
                  Xerxes Dotiwalla and
                  Aurelien Chouard and
                  Vijaysai Patnaik and
                  Paul Tsui and
                  James Guo and
                  Yin Zhou and
                  Yuning Chai and
                  Benjamin Caine and
                  Vijay Vasudevan and
                  Wei Han and
                  Jiquan Ngiam and
                  Hang Zhao and
                  Aleksei Timofeev and
                  Scott Ettinger and
                  Maxim Krivokon and
                  Amy Gao and
                  Aditya Joshi and
                  Yu Zhang and
                  Jonathon Shlens and
                  Zhifeng Chen and
                  Dragomir Anguelov},
  title        = {Scalability in Perception for Autonomous Driving: Waymo Open Dataset},
  booktitle    = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020},
  pages        = {2443--2451},
  publisher    = {Computer Vision Foundation / {IEEE}},
  year         = {2020},
  url          = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Sun\_Scalability\_in\_Perception\_for\_Autonomous\_Driving\_Waymo\_Open\_Dataset\_CVPR\_2020\_paper.html},
  doi          = {10.1109/CVPR42600.2020.00252},
  timestamp    = {Wed, 20 Jul 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/cvpr/SunKDCPTGZCCVHN20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/HanZCYSANVSC20,
  author       = {Wei Han and
                  Zhengdong Zhang and
                  Benjamin Caine and
                  Brandon Yang and
                  Christoph Sprunk and
                  Ouais Alsharif and
                  Jiquan Ngiam and
                  Vijay Vasudevan and
                  Jonathon Shlens and
                  Zhifeng Chen},
  editor       = {Andrea Vedaldi and
                  Horst Bischof and
                  Thomas Brox and
                  Jan{-}Michael Frahm},
  title        = {Streaming Object Detection for 3-D Point Clouds},
  booktitle    = {Computer Vision - {ECCV} 2020 - 16th European Conference, Glasgow,
                  UK, August 23-28, 2020, Proceedings, Part {XVIII}},
  series       = {Lecture Notes in Computer Science},
  volume       = {12363},
  pages        = {423--441},
  publisher    = {Springer},
  year         = {2020},
  url          = {https://doi.org/10.1007/978-3-030-58523-5\_25},
  doi          = {10.1007/978-3-030-58523-5\_25},
  timestamp    = {Fri, 04 Dec 2020 16:19:08 +0100},
  biburl       = {https://dblp.org/rec/conf/eccv/HanZCYSANVSC20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ParkZJHCLWL20,
  author       = {Daniel S. Park and
                  Yu Zhang and
                  Ye Jia and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  Bo Li and
                  Yonghui Wu and
                  Quoc V. Le},
  editor       = {Helen Meng and
                  Bo Xu and
                  Thomas Fang Zheng},
  title        = {Improved Noisy Student Training for Automatic Speech Recognition},
  booktitle    = {Interspeech 2020, 21st Annual Conference of the International Speech
                  Communication Association, Virtual Event, Shanghai, China, 25-29 October
                  2020},
  pages        = {2817--2821},
  publisher    = {{ISCA}},
  year         = {2020},
  url          = {https://doi.org/10.21437/Interspeech.2020-1470},
  doi          = {10.21437/INTERSPEECH.2020-1470},
  timestamp    = {Tue, 09 Feb 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/ParkZJHCLWL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HanZZYCQGPW20,
  author       = {Wei Han and
                  Zhengdong Zhang and
                  Yu Zhang and
                  Jiahui Yu and
                  Chung{-}Cheng Chiu and
                  James Qin and
                  Anmol Gulati and
                  Ruoming Pang and
                  Yonghui Wu},
  editor       = {Helen Meng and
                  Bo Xu and
                  Thomas Fang Zheng},
  title        = {ContextNet: Improving Convolutional Neural Networks for Automatic
                  Speech Recognition with Global Context},
  booktitle    = {Interspeech 2020, 21st Annual Conference of the International Speech
                  Communication Association, Virtual Event, Shanghai, China, 25-29 October
                  2020},
  pages        = {3610--3614},
  publisher    = {{ISCA}},
  year         = {2020},
  url          = {https://doi.org/10.21437/Interspeech.2020-2059},
  doi          = {10.21437/INTERSPEECH.2020-2059},
  timestamp    = {Fri, 29 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/HanZZYCQGPW20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/GulatiQCPZYHWZW20,
  author       = {Anmol Gulati and
                  James Qin and
                  Chung{-}Cheng Chiu and
                  Niki Parmar and
                  Yu Zhang and
                  Jiahui Yu and
                  Wei Han and
                  Shibo Wang and
                  Zhengdong Zhang and
                  Yonghui Wu and
                  Ruoming Pang},
  editor       = {Helen Meng and
                  Bo Xu and
                  Thomas Fang Zheng},
  title        = {Conformer: Convolution-augmented Transformer for Speech Recognition},
  booktitle    = {Interspeech 2020, 21st Annual Conference of the International Speech
                  Communication Association, Virtual Event, Shanghai, China, 25-29 October
                  2020},
  pages        = {5036--5040},
  publisher    = {{ISCA}},
  year         = {2020},
  url          = {https://doi.org/10.21437/Interspeech.2020-3015},
  doi          = {10.21437/INTERSPEECH.2020-3015},
  timestamp    = {Fri, 29 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/GulatiQCPZYHWZW20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-01864,
  author       = {Wei Han and
                  Zhengdong Zhang and
                  Benjamin Caine and
                  Brandon Yang and
                  Christoph Sprunk and
                  Ouais Alsharif and
                  Jiquan Ngiam and
                  Vijay Vasudevan and
                  Jonathon Shlens and
                  Zhifeng Chen},
  title        = {Streaming Object Detection for 3-D Point Clouds},
  journal      = {CoRR},
  volume       = {abs/2005.01864},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.01864},
  eprinttype    = {arXiv},
  eprint       = {2005.01864},
  timestamp    = {Fri, 04 Dec 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-01864.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-03191,
  author       = {Wei Han and
                  Zhengdong Zhang and
                  Yu Zhang and
                  Jiahui Yu and
                  Chung{-}Cheng Chiu and
                  James Qin and
                  Anmol Gulati and
                  Ruoming Pang and
                  Yonghui Wu},
  title        = {ContextNet: Improving Convolutional Neural Networks for Automatic
                  Speech Recognition with Global Context},
  journal      = {CoRR},
  volume       = {abs/2005.03191},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.03191},
  eprinttype    = {arXiv},
  eprint       = {2005.03191},
  timestamp    = {Mon, 11 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-03191.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-03271,
  author       = {Chung{-}Cheng Chiu and
                  Arun Narayanan and
                  Wei Han and
                  Rohit Prabhavalkar and
                  Yu Zhang and
                  Navdeep Jaitly and
                  Ruoming Pang and
                  Tara N. Sainath and
                  Patrick Nguyen and
                  Liangliang Cao and
                  Yonghui Wu},
  title        = {{RNN-T} Models Fail to Generalize to Out-of-Domain Audio: Causes and
                  Solutions},
  journal      = {CoRR},
  volume       = {abs/2005.03271},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.03271},
  eprinttype    = {arXiv},
  eprint       = {2005.03271},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-03271.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-08100,
  author       = {Anmol Gulati and
                  James Qin and
                  Chung{-}Cheng Chiu and
                  Niki Parmar and
                  Yu Zhang and
                  Jiahui Yu and
                  Wei Han and
                  Shibo Wang and
                  Zhengdong Zhang and
                  Yonghui Wu and
                  Ruoming Pang},
  title        = {Conformer: Convolution-augmented Transformer for Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2005.08100},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.08100},
  eprinttype    = {arXiv},
  eprint       = {2005.08100},
  timestamp    = {Tue, 27 Oct 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-08100.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-09629,
  author       = {Daniel S. Park and
                  Yu Zhang and
                  Ye Jia and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  Bo Li and
                  Yonghui Wu and
                  Quoc V. Le},
  title        = {Improved Noisy Student Training for Automatic Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2005.09629},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.09629},
  eprinttype    = {arXiv},
  eprint       = {2005.09629},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-09629.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-06030,
  author       = {Jiahui Yu and
                  Wei Han and
                  Anmol Gulati and
                  Chung{-}Cheng Chiu and
                  Bo Li and
                  Tara N. Sainath and
                  Yonghui Wu and
                  Ruoming Pang},
  title        = {Universal {ASR:} Unify and Improve Streaming {ASR} with Full-context
                  Modeling},
  journal      = {CoRR},
  volume       = {abs/2010.06030},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.06030},
  eprinttype    = {arXiv},
  eprint       = {2010.06030},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-06030.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-10504,
  author       = {Yu Zhang and
                  James Qin and
                  Daniel S. Park and
                  Wei Han and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Quoc V. Le and
                  Yonghui Wu},
  title        = {Pushing the Limits of Semi-Supervised Learning for Automatic Speech
                  Recognition},
  journal      = {CoRR},
  volume       = {abs/2010.10504},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.10504},
  eprinttype    = {arXiv},
  eprint       = {2010.10504},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-10504.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-11148,
  author       = {Jiahui Yu and
                  Chung{-}Cheng Chiu and
                  Bo Li and
                  Shuo{-}Yiin Chang and
                  Tara N. Sainath and
                  Yanzhang He and
                  Arun Narayanan and
                  Wei Han and
                  Anmol Gulati and
                  Yonghui Wu and
                  Ruoming Pang},
  title        = {FastEmit: Low-latency Streaming {ASR} with Sequence-level Emission
                  Regularization},
  journal      = {CoRR},
  volume       = {abs/2010.11148},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.11148},
  eprinttype    = {arXiv},
  eprint       = {2010.11148},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-11148.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-12096,
  author       = {Thibault Doutre and
                  Wei Han and
                  Min Ma and
                  Zhiyun Lu and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Arun Narayanan and
                  Ananya Misra and
                  Yu Zhang and
                  Liangliang Cao},
  title        = {Improving Streaming Automatic Speech Recognition With Non-Streaming
                  Model Distillation On Unsupervised Data},
  journal      = {CoRR},
  volume       = {abs/2010.12096},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.12096},
  eprinttype    = {arXiv},
  eprint       = {2010.12096},
  timestamp    = {Tue, 27 Oct 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-12096.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-10798,
  author       = {Bo Li and
                  Anmol Gulati and
                  Jiahui Yu and
                  Tara N. Sainath and
                  Chung{-}Cheng Chiu and
                  Arun Narayanan and
                  Shuo{-}Yiin Chang and
                  Ruoming Pang and
                  Yanzhang He and
                  James Qin and
                  Wei Han and
                  Qiao Liang and
                  Yu Zhang and
                  Trevor Strohman and
                  Yonghui Wu},
  title        = {A Better and Faster End-to-End Model for Streaming {ASR}},
  journal      = {CoRR},
  volume       = {abs/2011.10798},
  year         = {2020},
  url          = {https://arxiv.org/abs/2011.10798},
  eprinttype    = {arXiv},
  eprint       = {2011.10798},
  timestamp    = {Tue, 07 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2011-10798.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/us/Han19a,
  author       = {Wei Han},
  title        = {Learning compact neural network representations with structural priors},
  school       = {University of Illinois Urbana-Champaign, {USA}},
  year         = {2019},
  url          = {https://hdl.handle.net/2142/105057},
  timestamp    = {Thu, 31 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/phd/us/Han19a.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/ChiuKPCSWHZPKNN19,
  author       = {Chung{-}Cheng Chiu and
                  Anjuli Kannan and
                  Rohit Prabhavalkar and
                  Zhifeng Chen and
                  Tara N. Sainath and
                  Yonghui Wu and
                  Wei Han and
                  Yu Zhang and
                  Ruoming Pang and
                  Sergey Kishchenko and
                  Patrick Nguyen and
                  Arun Narayanan and
                  Hank Liao and
                  Shuyuan Zhang},
  title        = {A Comparison of End-to-End Models for Long-Form Speech Recognition},
  booktitle    = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
                  2019, Singapore, December 14-18, 2019},
  pages        = {889--896},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/ASRU46091.2019.9003854},
  doi          = {10.1109/ASRU46091.2019.9003854},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/asru/ChiuKPCSWHZPKNN19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-11069,
  author       = {Jiquan Ngiam and
                  Benjamin Caine and
                  Wei Han and
                  Brandon Yang and
                  Yuning Chai and
                  Pei Sun and
                  Yin Zhou and
                  Xi Yi and
                  Ouais Alsharif and
                  Patrick Nguyen and
                  Zhifeng Chen and
                  Jonathon Shlens and
                  Vijay Vasudevan},
  title        = {StarNet: Targeted Computation for Object Detection in Point Clouds},
  journal      = {CoRR},
  volume       = {abs/1908.11069},
  year         = {2019},
  url          = {http://arxiv.org/abs/1908.11069},
  eprinttype    = {arXiv},
  eprint       = {1908.11069},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1908-11069.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-02242,
  author       = {Chung{-}Cheng Chiu and
                  Wei Han and
                  Yu Zhang and
                  Ruoming Pang and
                  Sergey Kishchenko and
                  Patrick Nguyen and
                  Arun Narayanan and
                  Hank Liao and
                  Shuyuan Zhang and
                  Anjuli Kannan and
                  Rohit Prabhavalkar and
                  Zhifeng Chen and
                  Tara N. Sainath and
                  Yonghui Wu},
  title        = {A comparison of end-to-end models for long-form speech recognition},
  journal      = {CoRR},
  volume       = {abs/1911.02242},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.02242},
  eprinttype    = {arXiv},
  eprint       = {1911.02242},
  timestamp    = {Thu, 26 Nov 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-02242.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-04838,
  author       = {Pei Sun and
                  Henrik Kretzschmar and
                  Xerxes Dotiwalla and
                  Aurelien Chouard and
                  Vijaysai Patnaik and
                  Paul Tsui and
                  James Guo and
                  Yin Zhou and
                  Yuning Chai and
                  Benjamin Caine and
                  Vijay Vasudevan and
                  Wei Han and
                  Jiquan Ngiam and
                  Hang Zhao and
                  Aleksei Timofeev and
                  Scott Ettinger and
                  Maxim Krivokon and
                  Amy Gao and
                  Aditya Joshi and
                  Yu Zhang and
                  Jonathon Shlens and
                  Zhifeng Chen and
                  Dragomir Anguelov},
  title        = {Scalability in Perception for Autonomous Driving: Waymo Open Dataset},
  journal      = {CoRR},
  volume       = {abs/1912.04838},
  year         = {2019},
  url          = {http://arxiv.org/abs/1912.04838},
  eprinttype    = {arXiv},
  eprint       = {1912.04838},
  timestamp    = {Wed, 20 Jul 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1912-04838.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/0002CLYWH18,
  author       = {Wei Han and
                  Shiyu Chang and
                  Ding Liu and
                  Mo Yu and
                  Michael Witbrock and
                  Thomas S. Huang},
  title        = {Image Super-Resolution via Dual-State Recurrent Networks},
  booktitle    = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018},
  pages        = {1654--1663},
  publisher    = {Computer Vision Foundation / {IEEE} Computer Society},
  year         = {2018},
  url          = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Han\_Image\_Super-Resolution\_via\_CVPR\_2018\_paper.html},
  doi          = {10.1109/CVPR.2018.00178},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cvpr/0002CLYWH18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/YangYX0JH18,
  author       = {Yingzhen Yang and
                  Jianchao Yang and
                  Ning Xu and
                  Wei Han and
                  Nebojsa Jojic and
                  Thomas S. Huang},
  title        = {3D-FilterMap: {A} Compact Architecture for Deep Convolutional Neural
                  Networks},
  booktitle    = {6th International Conference on Learning Representations, {ICLR} 2018,
                  Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings},
  publisher    = {OpenReview.net},
  year         = {2018},
  url          = {https://openreview.net/forum?id=Sk4\_LURHf},
  timestamp    = {Mon, 09 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iclr/YangYX0JH18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-01609,
  author       = {Yingzhen Yang and
                  Jianchao Yang and
                  Ning Xu and
                  Wei Han},
  title        = {Learning 3D-FilterMap for Deep Convolutional Neural Networks},
  journal      = {CoRR},
  volume       = {abs/1801.01609},
  year         = {2018},
  url          = {http://arxiv.org/abs/1801.01609},
  eprinttype    = {arXiv},
  eprint       = {1801.01609},
  timestamp    = {Mon, 09 Dec 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1801-01609.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-02704,
  author       = {Wei Han and
                  Shiyu Chang and
                  Ding Liu and
                  Mo Yu and
                  Michael Witbrock and
                  Thomas S. Huang},
  title        = {Image Super-Resolution via Dual-State Recurrent Networks},
  journal      = {CoRR},
  volume       = {abs/1805.02704},
  year         = {2018},
  url          = {http://arxiv.org/abs/1805.02704},
  eprinttype    = {arXiv},
  eprint       = {1805.02704},
  timestamp    = {Tue, 18 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1805-02704.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/TimofteAG0ZLSKN17,
  author       = {Radu Timofte and
                  Eirikur Agustsson and
                  Luc Van Gool and
                  Ming{-}Hsuan Yang and
                  Lei Zhang and
                  Bee Lim and
                  Sanghyun Son and
                  Heewon Kim and
                  Seungjun Nah and
                  Kyoung Mu Lee and
                  Xintao Wang and
                  Yapeng Tian and
                  Ke Yu and
                  Yulun Zhang and
                  Shixiang Wu and
                  Chao Dong and
                  Liang Lin and
                  Yu Qiao and
                  Chen Change Loy and
                  Woong Bae and
                  Jae Jun Yoo and
                  Yoseob Han and
                  Jong Chul Ye and
                  Jae{-}Seok Choi and
                  Munchurl Kim and
                  Yuchen Fan and
                  Jiahui Yu and
                  Wei Han and
                  Ding Liu and
                  Haichao Yu and
                  Zhangyang Wang and
                  Honghui Shi and
                  Xinchao Wang and
                  Thomas S. Huang and
                  Yunjin Chen and
                  Kai Zhang and
                  Wangmeng Zuo and
                  Zhimin Tang and
                  Linkai Luo and
                  Shaohui Li and
                  Min Fu and
                  Lei Cao and
                  Wen Heng and
                  Giang Bui and
                  Truc Le and
                  Ye Duan and
                  Dacheng Tao and
                  Ruxin Wang and
                  Xu Lin and
                  Jianxin Pang and
                  Jinchang Xu and
                  Yu Zhao and
                  Xiangyu Xu and
                  Jin{-}shan Pan and
                  Deqing Sun and
                  Yujin Zhang and
                  Xibin Song and
                  Yuchao Dai and
                  Xueying Qin and
                  Xuan{-}Phung Huynh and
                  Tiantong Guo and
                  Hojjat Seyed Mousavi and
                  Tiep Huu Vu and
                  Vishal Monga and
                  Crist{\'{o}}v{\~{a}}o Cruz and
                  Karen O. Egiazarian and
                  Vladimir Katkovnik and
                  Rakesh Mehta and
                  Arnav Kumar Jain and
                  Abhinav Agarwalla and
                  Ch V. Sai Praveen and
                  Ruofan Zhou and
                  Hongdiao Wen and
                  Che Zhu and
                  Zhiqiang Xia and
                  Zhengtao Wang and
                  Qi Guo},
  title        = {{NTIRE} 2017 Challenge on Single Image Super-Resolution: Methods and
                  Results},
  booktitle    = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition
                  Workshops, {CVPR} Workshops 2017, Honolulu, HI, USA, July 21-26, 2017},
  pages        = {1110--1121},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/CVPRW.2017.149},
  doi          = {10.1109/CVPRW.2017.149},
  timestamp    = {Tue, 20 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cvpr/TimofteAG0ZLSKN17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/FanSYLHYWWH17,
  author       = {Yuchen Fan and
                  Honghui Shi and
                  Jiahui Yu and
                  Ding Liu and
                  Wei Han and
                  Haichao Yu and
                  Zhangyang Wang and
                  Xinchao Wang and
                  Thomas S. Huang},
  title        = {Balanced Two-Stage Residual Networks for Image Super-Resolution},
  booktitle    = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition
                  Workshops, {CVPR} Workshops 2017, Honolulu, HI, USA, July 21-26, 2017},
  pages        = {1157--1164},
  publisher    = {{IEEE} Computer Society},
  year         = {2017},
  url          = {https://doi.org/10.1109/CVPRW.2017.154},
  doi          = {10.1109/CVPRW.2017.154},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cvpr/FanSYLHYWWH17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ChangZHYGTCWHH17,
  author       = {Shiyu Chang and
                  Yang Zhang and
                  Wei Han and
                  Mo Yu and
                  Xiaoxiao Guo and
                  Wei Tan and
                  Xiaodong Cui and
                  Michael Witbrock and
                  Mark A. Hasegawa{-}Johnson and
                  Thomas S. Huang},
  editor       = {Isabelle Guyon and
                  Ulrike von Luxburg and
                  Samy Bengio and
                  Hanna M. Wallach and
                  Rob Fergus and
                  S. V. N. Vishwanathan and
                  Roman Garnett},
  title        = {Dilated Recurrent Neural Networks},
  booktitle    = {Advances in Neural Information Processing Systems 30: Annual Conference
                  on Neural Information Processing Systems 2017, December 4-9, 2017,
                  Long Beach, CA, {USA}},
  pages        = {77--87},
  year         = {2017},
  url          = {https://proceedings.neurips.cc/paper/2017/hash/32bb90e8976aab5298d5da10fe66f21d-Abstract.html},
  timestamp    = {Tue, 18 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/nips/ChangZHYGTCWHH17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-02224,
  author       = {Shiyu Chang and
                  Yang Zhang and
                  Wei Han and
                  Mo Yu and
                  Xiaoxiao Guo and
                  Wei Tan and
                  Xiaodong Cui and
                  Michael Witbrock and
                  Mark Hasegawa{-}Johnson and
                  Thomas S. Huang},
  title        = {Dilated Recurrent Neural Networks},
  journal      = {CoRR},
  volume       = {abs/1710.02224},
  year         = {2017},
  url          = {http://arxiv.org/abs/1710.02224},
  eprinttype    = {arXiv},
  eprint       = {1710.02224},
  timestamp    = {Tue, 18 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1710-02224.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tip/LiuWWYHH16,
  author       = {Ding Liu and
                  Zhaowen Wang and
                  Bihan Wen and
                  Jianchao Yang and
                  Wei Han and
                  Thomas S. Huang},
  title        = {Robust Single Image Super-Resolution via Deep Networks With Sparse
                  Prior},
  journal      = {{IEEE} Trans. Image Process.},
  volume       = {25},
  number       = {7},
  pages        = {3194--3207},
  year         = {2016},
  url          = {https://doi.org/10.1109/TIP.2016.2564643},
  doi          = {10.1109/TIP.2016.2564643},
  timestamp    = {Sun, 10 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tip/LiuWWYHH16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HanKPRBSLYH16,
  author       = {Wei Han and
                  Pooya Khorrami and
                  Tom Le Paine and
                  Prajit Ramachandran and
                  Mohammad Babaeizadeh and
                  Honghui Shi and
                  Jianan Li and
                  Shuicheng Yan and
                  Thomas S. Huang},
  title        = {Seq-NMS for Video Object Detection},
  journal      = {CoRR},
  volume       = {abs/1602.08465},
  year         = {2016},
  url          = {http://arxiv.org/abs/1602.08465},
  eprinttype    = {arXiv},
  eprint       = {1602.08465},
  timestamp    = {Wed, 15 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/HanKPRBSLYH16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/WangYWCHYH15,
  author       = {Zhangyang Wang and
                  Yingzhen Yang and
                  Zhaowen Wang and
                  Shiyu Chang and
                  Wei Han and
                  Jianchao Yang and
                  Thomas S. Huang},
  title        = {Self-tuned deep super resolution},
  booktitle    = {2015 {IEEE} Conference on Computer Vision and Pattern Recognition
                  Workshops, {CVPR} Workshops 2015, Boston, MA, USA, June 7-12, 2015},
  pages        = {1--8},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/CVPRW.2015.7301266},
  doi          = {10.1109/CVPRW.2015.7301266},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cvpr/WangYWCHYH15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccv/WangLYHH15,
  author       = {Zhaowen Wang and
                  Ding Liu and
                  Jianchao Yang and
                  Wei Han and
                  Thomas S. Huang},
  title        = {Deep Networks for Image Super-Resolution with Sparse Prior},
  booktitle    = {2015 {IEEE} International Conference on Computer Vision, {ICCV} 2015,
                  Santiago, Chile, December 7-13, 2015},
  pages        = {370--378},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/ICCV.2015.50},
  doi          = {10.1109/ICCV.2015.50},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iccv/WangLYHH15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/ChangHTQAH15,
  author       = {Shiyu Chang and
                  Wei Han and
                  Jiliang Tang and
                  Guo{-}Jun Qi and
                  Charu C. Aggarwal and
                  Thomas S. Huang},
  editor       = {Longbing Cao and
                  Chengqi Zhang and
                  Thorsten Joachims and
                  Geoffrey I. Webb and
                  Dragos D. Margineantu and
                  Graham Williams},
  title        = {Heterogeneous Network Embedding via Deep Architectures},
  booktitle    = {Proceedings of the 21th {ACM} {SIGKDD} International Conference on
                  Knowledge Discovery and Data Mining, Sydney, NSW, Australia, August
                  10-13, 2015},
  pages        = {119--128},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2783258.2783296},
  doi          = {10.1145/2783258.2783296},
  timestamp    = {Fri, 09 Apr 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/kdd/ChangHTQAH15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/corr/PaineKHH14,
  author       = {Tom Le Paine and
                  Pooya Khorrami and
                  Wei Han and
                  Thomas S. Huang},
  editor       = {Yoshua Bengio and
                  Yann LeCun},
  title        = {An Analysis of Unsupervised Pre-training in Light of Recent Advances},
  booktitle    = {3rd International Conference on Learning Representations, {ICLR} 2015,
                  San Diego, CA, USA, May 7-9, 2015, Workshop Track Proceedings},
  year         = {2015},
  url          = {http://arxiv.org/abs/1412.6597},
  timestamp    = {Wed, 17 Jul 2019 10:40:54 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/PaineKHH14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangYWCHYH15,
  author       = {Zhangyang Wang and
                  Yingzhen Yang and
                  Zhaowen Wang and
                  Shiyu Chang and
                  Wei Han and
                  Jianchao Yang and
                  Thomas S. Huang},
  title        = {Self-Tuned Deep Super Resolution},
  journal      = {CoRR},
  volume       = {abs/1504.05632},
  year         = {2015},
  url          = {http://arxiv.org/abs/1504.05632},
  eprinttype    = {arXiv},
  eprint       = {1504.05632},
  timestamp    = {Wed, 15 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/WangYWCHYH15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLYHH15,
  author       = {Zhaowen Wang and
                  Ding Liu and
                  Jianchao Yang and
                  Wei Han and
                  Thomas S. Huang},
  title        = {Deeply Improved Sparse Coding for Image Super-Resolution},
  journal      = {CoRR},
  volume       = {abs/1507.08905},
  year         = {2015},
  url          = {http://arxiv.org/abs/1507.08905},
  eprinttype    = {arXiv},
  eprint       = {1507.08905},
  timestamp    = {Wed, 15 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/WangLYHH15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/crc/aggarwal14/ChangHLXKH14,
  author       = {Shiyu Chang and
                  Wei Han and
                  Xianming Liu and
                  Ning Xu and
                  Pooya Khorrami and
                  Thomas S. Huang},
  editor       = {Charu C. Aggarwal},
  title        = {Multimedia Classification},
  booktitle    = {Data Classification: Algorithms and Applications},
  pages        = {337--364},
  publisher    = {{CRC} Press},
  year         = {2014},
  url          = {http://www.crcnetbase.com/doi/abs/10.1201/b17320-13},
  doi          = {10.1201/B17320-13},
  timestamp    = {Mon, 15 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/books/crc/aggarwal14/ChangHLXKH14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics