Papers › Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification

Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification

27 Jul 2021arXiv:2107.12666archive 2025-07-28

Zefeng Ding, Changxing Ding, Zhiyin Shao, DaCheng Tao

Text-to-image person re-identification (ReID) aims to search for images containing a person of interest using textual descriptions. However, due to the significant modality gap and the large intra-class variance in textual descriptions, text-to-image ReID remains a challenging problem. Accordingly, in this paper, we propose a Semantically Self-Aligned Network (SSAN) to handle the above problems. First, we propose a novel method that automatically extracts semantically aligned part-level features from the two modalities. Second, we design a multi-view non-local network that captures the relationships between body parts, thereby establishing better correspondences between body parts and noun phrases. Third, we introduce a Compound Ranking (CR) loss that makes use of textual descriptions for other images of the same identity to provide extra supervision, thereby effectively reducing the intra-class variance in textual features. Finally, to expedite future research in text-to-image ReID, we build a new database named ICFG-PEDES. Extensive experiments demonstrate that SSAN outperforms state-of-the-art approaches by significant margins. Both the new ICFG-PEDES database and the SSAN code are available at https://github.com/zifyloo/SSAN.

PaperPDFCode

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

Code

zifyloo/SSAN officialmentioned in papermentioned 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

Image RetrievalPerson Re-IdentificationText based Person RetrievalText-based Person Retrieval with Noisy Correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval ICFG-PEDES SSAN rank-1 54.23 #1 of 1 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES SSAN R@1 61.37 #11 of 21 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES SSAN R@10 86.73 #11 of 21 Archive leaderboard report
Text based Person Retrieval CUHK-PEDES SSAN R@5 80.15 #11 of 21 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES SSAN R@1 54.23 #11 of 12 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES SSAN Rank 10 77.42 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES SSAN Rank-1 46.52 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES SSAN Rank-5 68.36 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES SSAN mAP 42.49 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES SSAN mINP 28.13 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES SSAN Rank 1 40.57 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES SSAN Rank-10 71.53 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES SSAN Rank-5 62.58 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES SSAN mAP 20.93 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES SSAN mINP 2.22 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid SSAN Rank 1 35.10 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid SSAN Rank 10 71.45 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid SSAN Rank 5 60.00 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid SSAN mAP 28.90 #6 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid SSAN mINP 12.08 #6 of 6 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