Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification

By Shuangjie Xu, Yu Cheng, Kang Gu, Shiyu Chang, Pan Zhou. IEEE International Conference on Computer Vision, 2017

333 citations recorded by the source corpus.

Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of the current input video sequences, in a way that interdependency from the matching items can directly influence the computation of each other's representation. Specifically, the spatial pooling layer is able to select regions from each frame, while the attention temporal pooling performed can select informative frames over the sequence, both pooling guided by the information from distance matching. Experiments are conduced on the iLIDS-VID, PRID-2011 and MARS datasets and the results demonstrate that this approach outperforms existing state-of-art methods. We also analyze how the joint pooling in both dimensions can boost the person re-id performance more effectively than using either of them separately 1.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5ee96d5c4d467d00909472e3bc0d2c2d82ccb961

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild (2018, methodology): “IDE [53], QAN [26], ASTPN [44]) to update the deep feature representation learning.”
Exploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning (2018, background): “Another commonly used architecture is the Siamese network architecture [18, 29, 32], which also achieve reasonably good performance.”
Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN (2023, background): “Generally, they can be grouped into four categories: spatial attention [26], [28], [29], [31], channel attention [26], [27], [45], temporal attention [46], [47], and branch attention [48], [49].”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “The attention scheme is incorporated into a joint Spatial and Temporal Attention Pooling Network (ASTPN) [134] to select informative frames from the video sequence, extracting informative video representations.”
Mask-Guided Contrastive Attention Model for Person Re-identification (2018, methodology): “Following the previous work in [41], we also jointly train the network under Siamese loss and identity loss to further improve the performance of person ReID.”
Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification (2018, background): “For example, in [33, 26], high-quality local patterns are explored from images or videos ﬁrstly and then aggregated into informative feature vectors; in [28, 39, 49], local features of recurrent appearance data are extracted and integrated using temporal-pooling strategy; in [14, 5], to enhance the…”
Object Detection With Deep Learning: A Review (2018, background): “Recently, pedestrian detection has been intensively studied, which has a close relationship to pedestrian tracking [189], [190], person reidentification [191], [192], and robot navigation [193], [194].”