Papers › See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval

See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval

18 Aug 2022arXiv:2208.08608archive 2025-07-28

Xiujun Shu, Wei Wen, Haoqian Wu, Keyu Chen, Yiran Song, Ruizhi Qiao, Bo Ren, Xiao Wang

Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to obtain explicitly cross-modal alignments or utilize attention to explore salient alignments. These methods have two shortcomings: 1) Labeling cross-modal alignments are time-consuming. 2) Attention methods can explore salient cross-modal alignments but may ignore some subtle and valuable pairs. To relieve these issues, we introduce an Implicit Visual-Textual (IVT) framework for text-based person retrieval. Different from previous models, IVT utilizes a single network to learn representation for both modalities, which contributes to the visual-textual interaction. To explore the fine-grained alignment, we further propose two implicit semantic alignment paradigms: multi-level alignment (MLA) and bidirectional mask modeling (BMM). The MLA module explores finer matching at sentence, phrase, and word levels, while the BMM module aims to mine \textbf{more} semantic alignments between visual and textual modalities. Extensive experiments are carried out to evaluate the proposed IVT on public datasets, i.e., CUHK-PEDES, RSTPReID, and ICFG-PEDES. Even without explicit body part alignment, our approach still achieves state-of-the-art performance. Code is available at: https://github.com/TencentYoutuResearch/PersonRetrieval-IVT.

PaperPDFCode

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

Code

tencentyouturesearch/personretrieval-ivt 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

Person RetrievalRetrievalSentenceText based Person RetrievalText-based Person RetrievalText-based Person Retrieval with Noisy Correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES IVT Rank 10 85.61 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES IVT Rank-1 58.59 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES IVT Rank-5 78.51 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES IVT mAP 57.19 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES IVT mINP 45.78 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES IVT Rank 1 50.21 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES IVT Rank-10 76.18 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES IVT Rank-5 69.14 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES IVT mAP 34.72 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES IVT mINP 8.77 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid IVT Rank 1 43.65 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid IVT Rank 10 75.70 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid IVT Rank 5 66.50 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid IVT mAP 37.22 #5 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid IVT mINP 20.47 #5 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