Papers › Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-Identification

Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-Identification

1 Jan 2021ICCV 2021 10archive 2025-07-28

Yingquan Wang, Pingping Zhang, Shang Gao, Xia Geng, Hu Lu, Dong Wang

Video-based person re-identification aims to associate the video clips of the same person across multiple non-overlapping cameras. Spatial-temporal representations can provide richer and complementary information between frames, which are crucial to distinguish the target person when occlusion occurs. This paper proposes a novel Pyramid Spatial-Temporal Aggregation (PSTA) framework to aggregate the frame-level features progressively and fuse the hierarchical temporal features into a final video-level representation. Thus, short-term and long-term temporal information could be well exploited by different hierarchies. Furthermore, a Spatial-Temporal Aggregation Module (STAM) is proposed to enhance the aggregation capability of PSTA. It mainly consists of two novel attention blocks: Spatial Reference Attention (SRA) and Temporal Reference Attention (TRA). SRA explores the spatial correlations within a frame to determine the attention weight of each location. While TRA extends SRA with the correlations between adjacent frames, temporal consistency information can be fully explored to suppress the interference features and strengthen the discriminative ones. Extensive experiments on several challenging benchmarks demonstrate the effectiveness of the proposed PSTA, and our full model reaches 91.5% and 98.3% Rank-1 accuracy on MARS and DukeMTMC-VID benchmarks.

PaperPDFCode

Code

WangYQ9/VideoReID_PSTA officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Person Re-IdentificationVideo-Based Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-VideoReID PSTA mAP 97.4 #1 of 2 Archive leaderboard report
Person Re-Identification MARS PSTA mAP 85.8 #7 of 21 Archive leaderboard report
Person Re-Identification iLIDS-VID PSTA Rank-1 91.5 #4 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections