Papers › Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person...

Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification

11 Sep 2020arXiv:2009.05250archive 2025-07-28

Fufu Yu, Xinyang Jiang, Yifei Gong, Shizhen Zhao, Xiaowei Guo, Wei-Shi Zheng, Feng Zheng, Xing Sun

Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-pointand similar clothing still bring great challenges. Besides overall visual features, matching and comparing detailed information is also essential for tackling these challenges. This paper proposes two key recognition patterns to better utilize the detail information of pedestrian images, that most of the existing methods are unable to satisfy. Firstly, Visual Clue Alignment requires the model to select and align decisive regions pairs from two images for pair-wise comparison, while existing methods only align regions with predefined rules like high feature similarity or same semantic labels. Secondly, the Conditional Feature Embedding requires the overall feature of a query image to be dynamically adjusted based on the gallery image it matches, while most of the existing methods ignore the reference images. By introducing novel techniques including correspondence attention module and discrepancy-based GCN, we propose an end-to-end ReID method that integrates both patterns into a unified framework, called CACE-Net((C)lue(A)lignment and (C)onditional (E)mbedding). The experiments show that CACE-Net achieves state-of-the-art performance on three public datasets.

PaperPDFCode

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

Code

TencentYoutuResearch/PersonReID-CACENET officialmentioned on GitHubtfNOASSERTION 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-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03-C CaceNet Rank-1 17.04 #1 of 8 Archive leaderboard report
Person Re-Identification CUHK03-C CaceNet mAP 10.62 #1 of 8 Archive leaderboard report
Person Re-Identification CUHK03-C CaceNet mINP 2.09 #1 of 8 Archive leaderboard report
Person Re-Identification DukeMTMC-reID CACENET (ResNet50 w/o RK) Rank-1 90.89 #38 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID CACENET (ResNet50 w/o RK) mAP 81.29 #38 of 94 Archive leaderboard report
Person Re-Identification MSMT17 CACENET (ResNet50 w/o RR) Rank-1 83.54 #30 of 43 Archive leaderboard report
Person Re-Identification MSMT17 CACENET (ResNet50 w/o RR) mAP 62.00 #30 of 43 Archive leaderboard report
Person Re-Identification Market-1501 CACENET (Resnet50 without RR) Rank-1 95.96 #35 of 135 Archive leaderboard report
Person Re-Identification Market-1501 CACENET (Resnet50 without RR) mAP 90.30 #35 of 135 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

GCN

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