Pattern Recognition, Volume 103

Volume 103, July 2020

Features

• 
  Hei Long Chan, Tsz Chun Yam, Lok Ming Lui:
  Automatic characteristic-calibrated registration (ACC-REG): Hippocampal surface registration using eigen-graphs. 107142

Objects and image analysis

• 
  Lucas Correia Ribas, Jarbas Joaci de Mesquita Sá Junior, Leonardo F. S. Scabini, Odemir M. Bruno:
  Fusion of complex networks and randomized neural networks for texture analysis. 107189

Special Section on Deep Video Analysis: Models, Algorithms and Applications

• 
  Zhe Ren, Junchi Yan, Xiaokang Yang, Alan L. Yuille, Hongyuan Zha:
  Unsupervised learning of optical flow with patch consistency and occlusion estimation. 107191

Structural pattern recognition, network and graph methods

• 
  Xenophon Evangelopoulos, Austin J. Brockmeier, Tingting Mu, John Yannis Goulermas:
  Circular object arrangement using spherical embeddings. 107192

Objects and image analysis

• 
  Xing Wei, Haitao Zhang, Shaofan Liu, Yang Lu:
  Pedestrian detection in underground mines via parallel feature transfer network. 107195

Special Section on Deep Video Analysis: Models, Algorithms and Applications

• 
  Xiaoyan Cao, Shihui Guo, Juncong Lin, Wenshu Zhang, Minghong Liao:
  Online tracking of ants based on deep association metrics: method, dataset and evaluation. 107233

Machine learning

• 
  Ngoc Tran, Jean-Guy Schneider, Ingo Weber, A. Kai Qin:
  Hyper-parameter optimization in classification: To-do or not-to-do. 107245

Clustering

• 
  Stuart Golodetz, Anurag Arnab, Irina Voiculescu, Stephen Cameron:
  Simplifying TugGraph using zipping algorithms. 107257

Special Section on Deep Video Analysis: Models, Algorithms and Applications

• 
  Yang Li, Kan Li, Xinxin Wang, Richard Yi Da Xu:
  Exploring temporal consistency for human pose estimation in videos. 107258

Features

• 
  Muhammad Farhan Mughal, Ming Ronnier Luo, Michael R. Pointer:
  Modelling visual impressions for Chinese and Pakistani ethnic groups. 107259

Machine learning

• 
  Zhibao Tian, Hui Zhang, Yong Chen, Dell Zhang:
  Unsupervised hashing based on the recovery of subspace structures. 107261

Objects and image analysis

• 
  Jitka Kostková, Jan Flusser, Matej Lébl, Matteo Pedone:
  Handling Gaussian blur without deconvolution. 107264

Clustering

• 
  Hui Qv, Jihao Yin, Xiaoyan Luo:
  LG: A clustering framework supported by point proximity relations. 107265

Objects and image analysis

• 
  Wenliang Qiu, Xinbo Gao, Bing Han:
  Saliency detection using a deep conditional random field network. 107266

Special Section on Deep Video Analysis: Models, Algorithms and Applications

• 
  Tingting Han, Hongxun Yao, Wenlong Xie, Xiaoshuai Sun, Sicheng Zhao, Jun Yu:
  TVENet: Temporal variance embedding network for fine-grained action representation. 107267

Machine learning

• 
  Yingjun Xiong, Yan Xu, Xin Shu:
  Cross-view hashing via supervised deep discrete matrix factorization. 107270

Objects and image analysis

• 
  Yinyu Nie, Shihui Guo, Jian Chang, Xiaoguang Han, Jiahui Huang, Shi-Min Hu, Jian-Jun Zhang:
  Shallow2Deep: Indoor scene modeling by single image understanding. 107271

Features

• 
  Huan Zhao, Minjie Tang, Han Ding:
  HoPPF: A novel local surface descriptor for 3D object recognition. 107272

Face and biometrics

• 
  Baicun Zhou, Congying Han, Yonghong Liu, Tiande Guo, Jin Qin:
  Fast minutiae extractor using neural network. 107273

Machine learning

• 
  Zhihui Wang, Xinchen Ye, Baoli Sun, Jingyu Yang, Rui Xu, Haojie Li:
  Depth upsampling based on deep edge-aware learning. 107274

Objects and image analysis

• 
  Zheng Wang, Ziqi Zhou, Huchuan Lu, Jianmin Jiang:
  Global and local sensitivity guided key salient object re-augmentation for video saliency detection. 107275

Human movements and activities

• 
  Xishuai Peng, Yi Lu Murphey, Ruirui Liu, Yuanxiang Li:
  Driving maneuver early detection via sequence learning from vehicle signals and video images. 107276

Face and biometrics

• 
  Xingbo Dong, Soohyung Kim, Zhe Jin, Jung Yeon Hwang, Sangrae Cho, Andrew Beng Jin Teoh:
  Open-set face identification with index-of-max hashing by learning. 107277

Objects and image analysis

• 
  Carlos Cuevas, Daniel Quilon, Narciso García:
  Automatic soccer field of play registration. 107278

Human movements and activities

• 
  Ye-Ji Kim, Dong-Gyu Lee, Seong-Whan Lee:
  Three-stream fusion network for first-person interaction recognition. 107279

Classifiers and classification

• 
  Petr Hurtík, Vojtech Molek, Irina Perfilieva:
  Novel dimensionality reduction approach for unsupervised learning on small datasets. 107291

Objects and image analysis

• 
  Kun He, Dan Wang, Miao Tong, Zhijuan Zhu:
  An improved GrabCut on multiscale features. 107292

Human movements and activities

• 
  Yanshan Li, Rongjie Xia, Xing Liu:
  Learning shape and motion representations for view invariant skeleton-based action recognition. 107293

Special Section on Deep Video Analysis: Models, Algorithms and Applications

• 
  Yuming Fang, Chi Zhang, Xiongkuo Min, Hanqin Huang, Yugen Yi, Guangtao Zhai, Chia-Wen Lin:
  DevsNet: Deep Video Saliency Network using Short-term and Long-term Cues. 107294

Objects and image analysis

• 
  Yan Ren, Adams Wai-Kin Kong, Licheng Jiao:
  A survey on image and video cosegmentation: Methods, challenges and analyses. 107297

Classifiers and classification

• 
  Onuwa Okwuashi, Christopher E. Ndehedehe:
  Deep support vector machine for hyperspectral image classification. 107298

Objects and image analysis

• 
  Mingzhe Wang, Weichuan Zhang, Changming Sun, Arcot Sowmya:
  Corner detection based on shearlet transform and multi-directional structure tensor. 107299
• 
  Juncai Peng, Yuanjie Shao, Nong Sang, Changxin Gao:
  Joint image deblurring and matching with feature-based sparse representation prior. 107300

Clustering

• 
  Vanel Steve Siyou Fotso, Engelbert Mephu Nguifo, Philippe Vaslin:
  Frobenius correlation based u-shapelets discovery for time series clustering. 107301

Objects and image analysis

• 
  Zhiqiang Ma, Dongjoon Kim, Yeong-Gil Shin:
  Shape-from-focus reconstruction using nonlocal matting Laplacian prior followed by MRF-based refinement. 107302
• 
  Sina Mohammadi, Mehrdad Noori, Ali Bahri, Sina Ghofrani Majelan, Mohammad Havaei:
  CAGNet: Content-Aware Guidance for Salient Object Detection. 107303
• 
  Yuanqiang Cai, Weiqiang Wang, Yuting Chen, Qixiang Ye:
  IOS-Net: An inside-to-outside supervision network for scale robust text detection in the wild. 107304

Handwriting and document analysis

• 
  Jianshu Zhang, Jun Du, Lirong Dai:
  Radical analysis network for learning hierarchies of Chinese characters. 107305

Machine learning

• 
  Debasis Ganguly:
  Learning variable-length representation of words. 107306

Data science and big data

• 
  Morteza Ashraphijuo, Xiaodong Wang, Vaneet Aggarwal:
  Fundamental sampling patterns for low-rank multi-view data completion. 107307

Objects and image analysis

• 
  Ao Luo, Xin Li, Fan Yang, Zhicheng Jiao, Hong Cheng:
  Webly-supervised learning for salient object detection. 107308

Machine learning

• 
  Shuang Xu, Chunxia Zhang, Jiangshe Zhang:
  Adaptive quantile low-rank matrix factorization. 107310

Human movements and activities

• 
  Dejun Zhang, Linchao He, Zhigang Tu, Shifu Zhang, Fei Han, Boxiong Yang:
  Learning motion representation for real-time spatio-temporal action localization. 107312
• 
  Zhixiong Nan, Tianmin Shu, Ran Gong, Shu Wang, Ping Wei, Song-Chun Zhu, Nanning Zheng:
  Learning to infer human attention in daily activities. 107314

Clustering

• 
  Margot Selosse, Julien Jacques, Christophe Biernacki:
  Textual data summarization using the Self-Organized Co-Clustering model. 107315

Human movements and activities

• 
  Hui Yuan, Mengyu Li, Junhui Hou, Jimin Xiao:
  Single image-based head pose estimation with spherical parametrization and 3D morphing. 107316

Machine learning

• 
  Uras Mutlu, Ethem Alpaydin:
  Training bidirectional generative adversarial networks with hints. 107320

Special Section on Deep Video Analysis: Models, Algorithms and Applications

• 
  Yuxin Chen, Gaoqun Ma, Chunfeng Yuan, Bing Li, Hui Zhang, Fangshi Wang, Weiming Hu:
  Graph convolutional network with structure pooling and joint-wise channel attention for action recognition. 107321

Features

• 
  Wei Lian, Lei Zhang:
  A concave optimization algorithm for matching partially overlapping point sets. 107322

Face and biometrics

• 
  Jun Beom Kho, Andrew Beng Jin Teoh, Wonjune Lee, Jaihie Kim:
  Bit-string representation of a fingerprint image by normalized local structures. 107323

Objects and image analysis

• 
  Khalid M. Hosny, Mohamed M. Darwish, Tarek Aboelenen:
  New fractional-order Legendre-Fourier moments for pattern recognition applications. 107324

Classifiers and classification

• 
  Yashuang Mu, Xiaodong Liu, Lidong Wang, Juxiang Zhou:
  A parallel fuzzy rule-base based decision tree in the framework of map-reduce. 107326