Pattern Recognition, Volume 147

Volume 147, March 2024

Face and biometrics

• 
  Meiling Fang, Wufei Yang, Arjan Kuijper, Vitomir Struc, Naser Damer:
  Fairness in face presentation attack detection. 110002

Features

• 
  Shuqin Huang, Shasha Ren, Wei Wu, Qiong Liu:
  Discriminative features enhancement for low-altitude UAV object detection. 110041

Objects and image analysis

• 
  Jiabei Wang, Yanwei Pang, Jiale Cao, Hanqing Sun, Zhuang Shao, Xuelong Li:
  Deep intra-image contrastive learning for weakly supervised one-step person search. 110047

Human movements and activities

• 
  Zhanpeng Shao, Xueping Wang, Wen Zhou, Wuzhen Wang, Jianyu Yang, Youfu Li:
  A temporal densely connected recurrent network for event-based human pose estimation. 110048

Face and biometrics

• 
  Kaibing Zhang, Dongdong Zheng, Jie Li, Xinbo Gao, Jian Lu:
  Coupled discriminative manifold alignment for low-resolution face recognition. 110049

Various applications

• 
  Matt Poyser, Toby P. Breckon:
  Neural architecture search: A contemporary literature review for computer vision applications. 110052

Objects and image analysis

• 
  Pengcheng Zhang, Xiaohan Yu, Xiao Bai, Chen Wang, Jin Zheng, Xin Ning:
  Joint discriminative representation learning for end-to-end person search. 110053

Machine learning

• 
  Ahmadreza Sezavar, Randa Atta, Mohammed Ghanbari:
  DCapsNet: Deep capsule network for human activity and gait recognition with smartphone sensors. 110054

Classifiers and classification

• 
  Zichang Tan, Jun Li, Jinhao Du, Jun Wan, Zhen Lei, Guodong Guo:
  NCL++: Nested Collaborative Learning for long-tailed visual recognition. 110064

Machine learning

• 
  Furkan Mumcu, Yasin Yilmaz:
  Sequential architecture-agnostic black-box attack design and analysis. 110066

Objects and image analysis

• 
  Joonhyeok Moon, Munsu Jeon, Siheon Jeong, Ki-Yong Oh:
  RoMP-transformer: Rotational bounding box with multi-level feature pyramid transformer for object detection. 110067

Various applications

• 
  Vedant Vasant Dere, Amita A. Shinde, Prachi Vast:
  Conditional reiterative High-Fidelity GAN inversion for image editing. 110068

Bio-medical patterns

• 
  Xiaoqing Zhang, Zunjie Xiao, Bing Yang, Xiao Wu, Risa Higashita, Jiang Liu:
  Regional context-based recalibration network for cataract recognition in AS-OCT. 110069

Machine learning

• 
  Wenfeng Song, Shuai Li, Tao Chang, Ke Xie, Aimin Hao, Hong Qin:
  Dynamic attention augmented graph network for video accident anticipation. 110071
• 
  Qingqiang Chen, Gaoxia Jiang, Fuyuan Cao, Changqian Men, Wenjian Wang:
  A general elevating framework for label noise filters. 110072

Objects and image analysis

• 
  Benyi Yang, Zhenyu Liu, Guifang Duan, Jianrong Tan:
  Residual shape adaptive dense-nested Unet: Redesign the long lateral skip connections for metal surface tiny defect inspection. 110073
• 
  Bin Wan, Chengtao Lv, Xiaofei Zhou, Yaoqi Sun, Zunjie Zhu, Hongkui Wang, Chenggang Yan:
  TMNet: Triple-modal interaction encoder and multi-scale fusion decoder network for V-D-T salient object detection. 110074

Bio-medical patterns

• 
  Chenxi Sun, Hongyan Li, Moxian Song, Derun Cai, Baofeng Zhang, Shenda Hong:
  Time pattern reconstruction for classification of irregularly sampled time series. 110075

Objects and image analysis

• 
  Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang:
  Exploiting sublimated deep features for image retrieval. 110076

Various applications

• 
  Chuntao Zhu, Bolin Zhang, Qilin Yin, Chengxi Yin, Wei Lu:
  Deepfake detection via inter-frame inconsistency recomposition and enhancement. 110077

Objects and image analysis

• 
  Ge Song, Hanwen Su, Kai Huang, Fengyi Song, Ming Yang:
  Deep self-enhancement hashing for robust multi-label cross-modal retrieval. 110079

Classifiers and classification

• 
  Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schönlieb, Matthew Thorpe, Konstantinos C. Zygalakis:
  A linear transportation Lp distance for pattern recognition. 110080
• 
  Jinghua Liu, Wei Wei, Yaojin Lin, Lijie Yang, Hongbo Zhang:
  Learning implicit labeling-importance and label correlation for multi-label feature selection with streaming labels. 110081

Clustering

• 
  Zequn Yang, Han Zhang, Yake Wei, Zheng Wang, Feiping Nie, Di Hu:
  Geometric-inspired graph-based Incomplete Multi-view Clustering. 110082

Various applications

• 
  Xin Chen, Bin Wang, Yongsheng Gao:
  Separated Fan-Beam Projection with Gaussian Convolution for Invariant and Robust Butterfly Image Retrieval. 110083

Classifiers and classification

• 
  Chongqing Chen, Dezhi Han, Chin-Chen Chang:
  MPCCT: Multimodal vision-language learning paradigm with context-based compact Transformer. 110084
• 
  Xianheng Wang, Zhaobin Liu, Veronica Liesaputra, Zhiyi Huang:
  Feature specific progressive improvement for salient object detection. 110085

Features

• 
  Rui Huang, Xuran Pan, Henry Zheng, Haojun Jiang, Zhifeng Xie, Cheng Wu, Shiji Song, Gao Huang:
  Joint representation learning for text and 3D point cloud. 110086

Human movements and activities

• 
  Zihao Liu, Danfeng Yan, Yuanqiang Cai, Yan Song:
  Spatio-temporal human action localization in indoor surveillances. 110087

Machine learning

• 
  Yi Ding, Dan Mu, Jiaqi Zhang, Zhen Qin, Li You, Zhiguang Qin, Yingkun Guo:
  A cascaded framework with cross-modality transfer learning for whole heart segmentation. 110088

Objects and image analysis

• 
  Yunzhong Hou, Stephen Gould, Liang Zheng:
  View-coherent correlation consistency for semi-supervised semantic segmentation. 110089

Features

• 
  Yifan Chen, Xuelong Li:
  Gait feature learning via spatio-temporal two-branch networks. 110090

Machine learning

• 
  Haitao Tian, Shiru Qu, Pierre Payeur:
  Learning a target-dependent classifier for cross-domain semantic segmentation: Fine-tuning versus meta-learning. 110091

Structural pattern recognition, network and graph methods

• 
  Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi:
  Region-adaptive and context-complementary cross modulation for RGB-T semantic segmentation. 110092

Objects and image analysis

• 
  Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong:
  Residual Deformable Convolution for better image de-weathering. 110093

Features

• 
  Kun Dai, Tao Xie, Ke Wang, Zhiqiang Jiang, Ruifeng Li, Lijun Zhao:
  OAMatcher: An overlapping areas-based network with label credibility for robust and accurate feature matching. 110094

Various applications

• 
  Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang:
  KGSR: A kernel guided network for real-world blind super-resolution. 110095

Classifiers and classification

• 
  Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao:
  F-SCP: An automatic prompt generation method for specific classes based on visual language pre-training models. 110096
• 
  Jae Soon Baik, In Young Yoon, Jun Won Choi:
  DBN-Mix: Training dual branch network using bilateral mixup augmentation for long-tailed visual recognition. 110107

Various applications

• 
  Karim Slimani, Catherine Achard, Brahim Tamadazte:
  RoCNet++: Triangle-based descriptor for accurate and robust point cloud registration. 110108

Classifiers and classification

• 
  Ziyun Cai, Yawen Huang, Tengfei Zhang, Xiao-Yuan Jing, Yefeng Zheng, Ling Shao:
  Attention Cycle-consistent universal network for More Universal Domain Adaptation. 110109

Human movements and activities

• 
  Xiang Wang, Shiwei Zhang, Zhiwu Qing, Zhengrong Zuo, Changxin Gao, Rong Jin, Nong Sang:
  HyRSM++: Hybrid relation guided temporal set matching for few-shot action recognition. 110110

Objects and image analysis

• 
  Zian Zhang, Yongqiang Zhang, Yin Zhang, Rui Tian, Mingli Ding:
  Vital information is only worth one thumbnail: Towards efficient human pose estimation. 110111

Features

• 
  Ronghao Xian, Xin Xiong, Hong Peng, Jun Wang, Antonio Ramírez-de-Arellano, Qian Yang:
  Feature fusion method based on spiking neural convolutional network for edge detection. 110112

Machine learning

• 
  Siddharth Ramchandran, Gleb Tikhonov, Otto Lönnroth, Pekka Tiikkainen, Harri Lähdesmäki:
  Learning conditional variational autoencoders with missing covariates. 110113
• 
  Minhao Zou, Zhongxue Gan, Yutong Wang, Junheng Zhang, Dongyan Sui, Chun Guan, Siyang Leng:
  UniG-Encoder: A universal feature encoder for graph and hypergraph node classification. 110115

Human movements and activities

• 
  Songlin Du, Zhiwei Yuan, Peifu Lai, Takeshi Ikenaga:
  JoyPose: Jointly learning evolutionary data augmentation and anatomy-aware global-local representation for 3D human pose estimation. 110116
• 
  Yunfei Yin, Li Jing, Faliang Huang, Guangchao Yang, Zhuowei Wang:
  MSA-GCN: Multiscale Adaptive Graph Convolution Network for gait emotion recognition. 110117

Various applications

• 
  Zheng Wang, Haowei Ran, Jinchang Ren, Meijun Sun:
  PWDformer: Deformable transformer for long-term series forecasting. 110118

Innovative Applications of Pattern Recognition

• 
  Ping He, Fan Zhang, Gang Li, Huibin Li:
  Adversarial and focused training of abnormal videos for weakly-supervised anomaly detection. 110119

Objects and image analysis

• 
  Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Xuelong Li, Yue Lu:
  Distance-based Weighted Transformer Network for image completion. 110120

Data science and big data

• 
  Michael Franklin Mbouopda, Engelbert Mephu Nguifo:
  Scalable and accurate subsequence transform for time series classification. 110121

Handwriting and document analysis

• 
  Chun Chet Ng, Che-Tsung Lin, Zhi Qin Tan, Xinyu Wang, Jie-Long Kew, Chee Seng Chan, Christopher Zach:
  When IC meets text: Towards a rich annotated integrated circuit text dataset. 110124

Classifiers and classification

• 
  Hui Liu, Bo Zhao, Jiabao Guo, Kehuan Zhang, Peng Liu:
  A lightweight unsupervised adversarial detector based on autoencoder and isolation forest. 110127

Objects and image analysis

• 
  Fudong Xu, Lin Wang, Huibin Li:
  A unified and efficient semi-supervised learning framework for stereo matching. 110128

Features

• 
  Xiaobo Hu, Jianbo Su, Jun Zhang:
  Disturbance rejection with compensation on features. 110129

Machine learning

• 
  Xabier Echeberria-Barrio, Amaia Gil-Lerchundi, Iñigo Mendialdua, Raul Orduna Urrutia:
  Topological safeguard for evasion attack interpreting the neural networks' behavior. 110130
• 
  Huihuang Zhao, Lin Zhang, Paul L. Rosin, Yu-Kun Lai, Yaonan Wang:
  HairManip: High quality hair manipulation via hair element disentangling. 110132

Classifiers and classification

• 
  Xiao Li, Min Fang, Zhibo Zhai:
  Joint Feature Generation and Open-set Prototype Learning for generalized zero-shot open-set classification. 110133
• 
  Khondaker Tasrif Noor, Antonio Robles-Kelly:
  H-CapsNet: A capsule network for hierarchical image classification. 110135
• 
  Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer:
  ConvGeN: A convex space learning approach for deep-generative oversampling and imbalanced classification of small tabular datasets. 110138

Objects and image analysis

• 
  Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang:
  CS-net: Conv-simpleformer network for agricultural image segmentation. 110140

Machine learning

• 
  Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe:
  ECLAD: Extracting Concepts with Local Aggregated Descriptors. 110146