See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-identification

By Zhen Zhou, Yan Huang, Liang Wang, Tien-Ping Tan. Computer Vision and Pattern Recognition, 2017

331 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d3312da8c703ed7842285289c3d9478f333dbd48

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. Yi Yang
2. Wanli Ouyang
3. G. Wang
4. Tao A. Xiang
5. Alex ChiChung Kot
6. Liang Wang
7. Xiaogang Wang
8. Shuang Li

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Ling Shao
3. Xiaogang Wang
4. Luc Van Gool
5. Dacheng Tao
6. Ming-Hsuan Yang
7. Tao A. Xiang
8. Wanli Ouyang

Citations in the corpus

• A Pose-Sensitive Embedding for Person Re-identification with Expanded Cross Neighborhood Re-ranking (2017, neutral): “2 - Forest [50] CVPR17 - - - - 50.”
• Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification (2018, methodology): “[52] combine spatial and temporal information by building an end-to-end deep neural network.”
• Discriminability Distillation in Group Representation Learning (2020, background): “They can be divided into three categories, RNNbased [39,61], attention-based [37,71] and 3D-Conv based [15].”
• Mask-Guided Contrastive Attention Model for Person Re-identification (2018, methodology): “In addition, some works try to introduce the pair-wise contrastive loss [14], triplet ranking loss [54] and quadruplet loss [8] to further enhance the IDE feature.”
• Exploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning (2018, methodology): “In [40], temporal attention information and spatial recurrent information are used to explore contextual representation.”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “A temporal attention model [133] is proposed to automatically select the most discriminative frames in a given video and integrate the contextual information with a spatial recurrent model.”
• Pose Transferrable Person Re-identification (2018, methodology): “Recently, DCNN is widely used in the filed of ReID [44, 19, 36, 4, 6, 55, 48].”
• Deep Cosine Metric Learning for Person Re-identification (2018, neutral): “70 CaffeNet [38] 70.”
• Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification (2018, methodology): “…feature sequences or body-part based semantic feature sets are extracted from pedestrian images and matched according to some heuristic correspondence structures; in [44, 43, 69], multiple sub-segment or frame level compar-1 isons are computed and aggregated for matching pedestrian based on video.”