Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search
Text-based person search (TPS), a critical technology for security and surveillance, aims to retrieve target individuals from image galleries using textual descriptions. The existing methods face two challenges: (1) ambiguous attribute–noun association (AANA), where syntactic ambiguities lead to inc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/9/7/182 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839616473405849600 |
|---|---|
| author | Wei Xia Wenguang Gan Xinpan Yuan |
| author_facet | Wei Xia Wenguang Gan Xinpan Yuan |
| author_sort | Wei Xia |
| collection | DOAJ |
| description | Text-based person search (TPS), a critical technology for security and surveillance, aims to retrieve target individuals from image galleries using textual descriptions. The existing methods face two challenges: (1) ambiguous attribute–noun association (AANA), where syntactic ambiguities lead to incorrect associations between attributes and the intended nouns; and (2) textual noise and relevance imbalance (TNRI), where irrelevant or non-discriminative tokens (e.g., ‘wearing’) reduce the saliency of critical visual attributes in the textual description. To address these aspects, we propose the dependency-aware entity–attribute alignment network (DEAAN), a novel framework that explicitly tackles AANA through dependency-guided attention and TNRI via adaptive token filtering. The DEAAN introduces two modules: (1) dependency-assisted implicit reasoning (DAIR) to resolve AANA through syntactic parsing, and (2) relevance-adaptive token selection (RATS) to suppress TNRI by learning token saliency. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate state-of-the-art performance, with the DEAAN achieving a Rank-1 accuracy of 76.71% and an mAP of 69.07% on CUHK-PEDES, surpassing RDE by 0.77% in Rank-1 and 1.51% in mAP. Ablation studies reveal that DAIR and RATS individually improve Rank-1 by 2.54% and 3.42%, while their combination elevates the performance by 6.35%, validating their synergy. This work bridges structured linguistic analysis with adaptive feature selection, demonstrating practical robustness in surveillance-oriented TPS scenarios. |
| format | Article |
| id | doaj-art-2bc8fde231a74029ab0d9eadd6d1edac |
| institution | Matheson Library |
| issn | 2504-2289 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj-art-2bc8fde231a74029ab0d9eadd6d1edac2025-07-25T13:14:09ZengMDPI AGBig Data and Cognitive Computing2504-22892025-07-019718210.3390/bdcc9070182Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person SearchWei Xia0Wenguang Gan1Xinpan Yuan2School of Computer, Hunan University of Technology, Zhuzhou 412000, ChinaSchool of Computer, Hunan University of Technology, Zhuzhou 412000, ChinaSchool of Computer, Hunan University of Technology, Zhuzhou 412000, ChinaText-based person search (TPS), a critical technology for security and surveillance, aims to retrieve target individuals from image galleries using textual descriptions. The existing methods face two challenges: (1) ambiguous attribute–noun association (AANA), where syntactic ambiguities lead to incorrect associations between attributes and the intended nouns; and (2) textual noise and relevance imbalance (TNRI), where irrelevant or non-discriminative tokens (e.g., ‘wearing’) reduce the saliency of critical visual attributes in the textual description. To address these aspects, we propose the dependency-aware entity–attribute alignment network (DEAAN), a novel framework that explicitly tackles AANA through dependency-guided attention and TNRI via adaptive token filtering. The DEAAN introduces two modules: (1) dependency-assisted implicit reasoning (DAIR) to resolve AANA through syntactic parsing, and (2) relevance-adaptive token selection (RATS) to suppress TNRI by learning token saliency. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate state-of-the-art performance, with the DEAAN achieving a Rank-1 accuracy of 76.71% and an mAP of 69.07% on CUHK-PEDES, surpassing RDE by 0.77% in Rank-1 and 1.51% in mAP. Ablation studies reveal that DAIR and RATS individually improve Rank-1 by 2.54% and 3.42%, while their combination elevates the performance by 6.35%, validating their synergy. This work bridges structured linguistic analysis with adaptive feature selection, demonstrating practical robustness in surveillance-oriented TPS scenarios.https://www.mdpi.com/2504-2289/9/7/182text-based person searchsyntactic knowledgesemantic alignment |
| spellingShingle | Wei Xia Wenguang Gan Xinpan Yuan Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search Big Data and Cognitive Computing text-based person search syntactic knowledge semantic alignment |
| title | Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search |
| title_full | Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search |
| title_fullStr | Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search |
| title_full_unstemmed | Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search |
| title_short | Dependency-Aware Entity–Attribute Relationship Learning for Text-Based Person Search |
| title_sort | dependency aware entity attribute relationship learning for text based person search |
| topic | text-based person search syntactic knowledge semantic alignment |
| url | https://www.mdpi.com/2504-2289/9/7/182 |
| work_keys_str_mv | AT weixia dependencyawareentityattributerelationshiplearningfortextbasedpersonsearch AT wenguanggan dependencyawareentityattributerelationshiplearningfortextbasedpersonsearch AT xinpanyuan dependencyawareentityattributerelationshiplearningfortextbasedpersonsearch |