Papers › Sequential End-to-end Network for Efficient Person Search

Sequential End-to-end Network for Efficient Person Search

18 Mar 2021arXiv:2103.10148archive 2025-07-28

Zhengjia Li, Duoqian Miao

Person search aims at jointly solving Person Detection and Person Re-identification (re-ID). Existing works have designed end-to-end networks based on Faster R-CNN. However, due to the parallel structure of Faster R-CNN, the extracted features come from the low-quality proposals generated by the Region Proposal Network, rather than the detected high-quality bounding boxes. Person search is a fine-grained task and such inferior features will significantly reduce re-ID performance. To address this issue, we propose a Sequential End-to-end Network (SeqNet) to extract superior features. In SeqNet, detection and re-ID are considered as a progressive process and tackled with two sub-networks sequentially. In addition, we design a robust Context Bipartite Graph Matching (CBGM) algorithm to effectively employ context information as an important complementary cue for person matching. Extensive experiments on two widely used person search benchmarks, CUHK-SYSU and PRW, have shown that our method achieves state-of-the-art results. Also, our model runs at 11.5 fps on a single GPU and can be integrated into the existing end-to-end framework easily.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

serend1p1ty/SeqNet officialmentioned on GitHubpytorch 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

Graph MatchingHuman DetectionPerson Re-IdentificationPerson SearchRegion Proposal

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Search CUHK-SYSU NAE+SeqNet+CBGM MAP 94.8 #8 of 16 Archive leaderboard report
Person Search CUHK-SYSU NAE+SeqNet+CBGM Top-1 95.7 #8 of 16 Archive leaderboard report
Person Search CUHK-SYSU OIM+SeqNet+CBGM MAP 94.3 #10 of 16 Archive leaderboard report
Person Search CUHK-SYSU OIM+SeqNet+CBGM Top-1 95.0 #10 of 16 Archive leaderboard report
Person Search CUHK-SYSU NAE+SeqNet MAP 93.8 #12 of 16 Archive leaderboard report
Person Search CUHK-SYSU NAE+SeqNet Top-1 94.6 #12 of 16 Archive leaderboard report
Person Search CUHK-SYSU OIM+SeqNet MAP 93.4 #13 of 16 Archive leaderboard report
Person Search CUHK-SYSU OIM+SeqNet Top-1 94.1 #13 of 16 Archive leaderboard report
Person Search PRW NAE+SeqNet+CBGM Top-1 87.6 #8 of 15 Archive leaderboard report
Person Search PRW NAE+SeqNet+CBGM mAP 47.6 #8 of 15 Archive leaderboard report
Person Search PRW NAE+SeqNet Top-1 83.4 #11 of 15 Archive leaderboard report
Person Search PRW NAE+SeqNet mAP 46.7 #11 of 15 Archive leaderboard report
Person Search PRW OIM+SeqNet+CBGM Top-1 84.9 #12 of 15 Archive leaderboard report
Person Search PRW OIM+SeqNet+CBGM mAP 46.6 #12 of 15 Archive leaderboard report
Person Search PRW OIM+SeqNet Top-1 81.7 #15 of 15 Archive leaderboard report
Person Search PRW OIM+SeqNet mAP 45.8 #15 of 15 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.

Methods

ConvolutionFaster R-CNNRPNRoIPoolSoftmax

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