Gait recognition without subject cooperation

By Khalid Bashir, Tao A. Xiang, Shaogang Gong. Pattern Recognition Letters, 2010

333 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/ca88d5e8a9d57dde0af641807e6e5a7e5926dc6c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Xiatian Zhu
2. Shaogang Gong
3. Yasushi Makihara
4. Yasushi Yagi
5. Daigo Muramatsu
6. Tomio Echigo
7. Junping Zhang
8. Jianfeng Feng

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Xiatian Zhu
3. Shaogang Gong
4. Liang Zheng
5. Xiaogang Wang
6. Luc Van Gool
7. Qi Tian
8. Dacheng Tao

In Human-Computer Interaction

1. Yasushi Makihara
2. Yasushi Yagi
3. Daigo Muramatsu
4. Tomio Echigo
5. Shaogang Gong
6. Shengjin Wang
7. Tardi Tjahjadi
8. Xiaoming Xiao

Citations in the corpus

• Person Re-identification by Video Ranking (2014, background): “Most gait recognition methods do not cope well with cluttered background and/or random occlusion with unknown covariate conditions [1].”
• GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “Third, they extract the representation of the gait by machine learning approaches such as Canonical Correlation Analysis (CCA) (Xing et al. 2016), Linear Discriminant Analysis (LDA) (Bashir, Xiang, and Gong 2010) and deep learning (Shiraga et al. 2016).”
• Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, methodology): “The 125 gait entropy image introduced in [28] is designed mainly for mitigating the effect of changes in covariate 126 conditions that affect gait feature extraction rather than the gait itself.”
• Recurrent Attention Models for Depth-Based Person Identification (2016, background): “Originally proposed in [26], the gait energy image and ifigts variants [16, 6, 29, 66], embed temporal information onto a two-dimensional image by averaging the silhouette across all frames of a video.”
• The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition (2012, methodology): “(d) CGI and GEnI.”
• GEINet: View-invariant gait recognition using a convolutional neural network (2016, methodology): “GEI [2] is constructed by first making a masking image using thresholding GEnI to preserve only the dynamic parts and masking the static part of the GEI.”
• Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition (2018, background): “On the other hand, the accuracies of the discriminative approach without CNN, i.e., LDA, and the generative approach, i.e., VTM and wQVTM, are a little bit better than that of DM except for the case of the rank 1 identification rate of wQVTM.”