{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T04:19:45Z","timestamp":1787804385986,"version":"build-2784847793"},"reference-count":26,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"crossref","award":["2023JJ50392"],"award-info":[{"award-number":["2023JJ50392"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100009377","name":"Scientific Research Fund of Hunan Provincial Education Department","doi-asserted-by":"publisher","award":["23A0588"],"award-info":[{"award-number":["23A0588"]}],"id":[{"id":"10.13039\/100009377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Text-based person search (TPS) suffers from cross-modal informational skewness: pedestrian images are high-dimensional and redundancy-prone, while textual descriptions are sparse, incomplete, and sometimes inaccurate. To address the low alignment accuracy and poor robustness caused by the inherent uneven information distribution of visual and textual modalities in TPS, this paper proposes a unified Partition-based Information Rebalancing (PaIR) framework to realize balanced optimization and precise alignment of cross-modal information from both global content and local part dimensions. The framework adopts the CLIP dual-modal encoder for basic feature extraction and constructs a parallel global\u2013local dual representation system to compensate for the lack of fine-grained spatial information in single global features. To eliminate modal redundancy and noise interference, a dual-modal noise suppression module is designed to filter invalid redundant information through visual foreground\u2013background separation and textual token weight screening, while introducing adversarial constraints and orthogonal constraints to purify effective features. On this basis, a part balance alignment module is built to complete human semantic part decomposition and soft matching alignment for dual-modal features. Aiming at the common part semantic missing problem in textual descriptions, a visual part correlation affinity matrix is utilized for semantic associative completion to balance the information density of dual modalities. Finally, a global\u2013local joint alignment strategy integrates hierarchical features and bidirectional cross-modal attention interaction to eliminate global\u2013local semantic discontinuity and enhance fine-grained cross-modal matching capability. Extensive experiments on three public benchmarks demonstrate that PaIR consistently improves multiple baselines.<\/jats:p>","DOI":"10.3390\/jimaging12090400","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:57:17Z","timestamp":1787662637000},"page":"400","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PaIR: Partition-Based Information Rebalancing for Robust Text-Based Person Search"],"prefix":"10.3390","volume":"12","author":[{"given":"Luda","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Science, Xiangnan University, Chenzhou 423000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1326-6008","authenticated-orcid":false,"given":"Jiabao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Science, Hunan University of Technology, Zhuzhou 412000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9509-0755","authenticated-orcid":false,"given":"Xinpan","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Science, Hunan University of Technology, Zhuzhou 412000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningdan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Science, Xiangnan University, Chenzhou 423000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"ref_1","unstructured":"Ding, Z., Ding, C., Shao, Z., and Tao, D. (2021). Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., and Ding, C. (2022, January 10\u201314). Learning granularity-unified representations for text-to-image person re-identification. Proceedings of the 30th ACM International Conference on Multimedia, Lisbon, Portugal.","DOI":"10.1145\/3503161.3548028"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Qin, Y., Chen, Y., Peng, D., Peng, X., Zhou, J.T., and Hu, P. (2024, January 16\u201322). Noisy-correspondence learning for text-to-image person re-identification. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhu, A., Wang, Z., Li, Y., Wan, X., Jin, J., Wang, T., Hu, F., and Hua, G. (2021, January 20\u201324). Dssl: Deep surroundings-person separation learning for text-based person retrieval. Proceedings of the 29th ACM International Conference on Multimedia, Virtual Event.","DOI":"10.1145\/3474085.3475369"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Qin, Y., Chen, C., Fu, Z., Peng, D., Peng, X., and Hu, P. (2025, January 11\u201315). Human-centered interactive learning via mllms for text-to-image person re-identification. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01342"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6032","DOI":"10.1109\/TIP.2023.3327924","article-title":"Clip-driven fine-grained text-image person re-identification","volume":"32","author":"Yan","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"26974","DOI":"10.1609\/aaai.v40i32.39910","article-title":"HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment","volume":"Volume 40","author":"Wu","year":"2026","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_8","unstructured":"Xie, C., Wang, B., Kong, F., Li, J., Liang, D., Ao, J., Leng, D., and Yin, Y. (2025). FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model. arXiv."},{"key":"ref_9","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021). Learning transferable visual models from natural language supervision. Proceedings of the International Conference on Machine Learning, PMLR."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1609\/aaai.v38i1.27801","article-title":"An empirical study of clip for text-based person search","volume":"Volume 38","author":"Cao","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"17973","DOI":"10.1109\/TNNLS.2023.3310118","article-title":"Image-specific information suppression and implicit local alignment for text-based person search","volume":"35","author":"Yan","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Tan, W., Ding, C., Jiang, J., Wang, F., Zhan, Y., and Tao, D. (2024, January 16\u201322). Harnessing the power of mllms for transferable text-to-image person reid. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Niu, K., Huang, Y., and Wang, L. (2020, January 12\u201316). Textual dependency embedding for person search by language. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3413895"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., and Wang, X. (2017, January 21\u201326). Person search with natural language description. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Aggarwal, S., Radhakrishnan, V.B., and Chakraborty, A. (2020, January 1\u20135). Text-based person search via attribute-aided matching. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Shu, X., Wen, W., Wu, H., Chen, K., Song, Y., Qiao, R., Ren, B., and Wang, X. (2022). See finer, see more: Implicit modality alignment for text-based person retrieval. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref_17","unstructured":"Yan, S., Dong, N., Liu, J., Zhang, L., and Tang, J. (November, January 29). Learning comprehensive representations with richer self for text-to-image person re-identification. Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, ON, Canada."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bai, Y., Cao, M., Gao, D., Cao, Z., Chen, C., Fan, Z., Nie, L., and Zhang, M. (2023). Rasa: Relation and sensitivity aware representation learning for text-based person search. arXiv.","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jiang, D., and Ye, M. (2023, January 17\u201324). Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zuo, J., Zhou, H., Nie, Y., Zhang, F., Guo, T., Sang, N., Wang, Y., and Gao, C. (2024, January 16\u201322). Ufinebench: Towards text-based person retrieval with ultra-fine granularity. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"132885","DOI":"10.1016\/j.neucom.2026.132885","article-title":"DiCo: Disentangled concept representation for text-to-image person re-identification","volume":"675","author":"Kim","year":"2026","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Parcalabescu, L., Cafagna, M., Muradjan, L., Frank, A., Calixto, I., and Gatt, A. (2022). VALSE: A task-independent benchmark for vision and language models centered on linguistic phenomena. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"9595","DOI":"10.1109\/TPAMI.2023.3247939","article-title":"Cross-modal retrieval with partially mismatched pairs","volume":"45","author":"Hu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","unstructured":"Wang, Y., Wang, L., Zhou, Q., Wang, Z., Li, H., Hua, G., and Tang, W. (November, January 28). Multimodal llm enhanced cross-lingual cross-modal retrieval. Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, VIC, Australia."},{"key":"ref_25","unstructured":"Chen, H., Lin, J., Chen, X., Fan, Y., Dong, J., Jin, X., Su, H., Fu, J., and Shen, X. (2025). Rethinking Visual Layer Selection in Multimodal LLMs. arXiv."},{"key":"ref_26","unstructured":"Zhou, J., Jiang, J., and Zhu, Z. (2025). Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation. arXiv."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/400\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T04:11:00Z","timestamp":1787803860000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":26,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jimaging12090400"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12090400","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]}}}