{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:10:45Z","timestamp":1784639445878,"version":"3.55.0"},"reference-count":31,"publisher":"Association for Computing Machinery (ACM)","issue":"10","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>\n            Text-Based Person Search (TBPS) is a problem that gained significant interest within the research community. The task is that of retrieving one or more images of a specific individual based on a textual description. The multi-modal nature of the task requires learning representations that bridge text and image data within a shared latent space. Existing TBPS systems face two major challenges. One is defined as\n            <jats:italic toggle=\"yes\">inter-identity<\/jats:italic>\n            noise that is due to the inherent vagueness and imprecision of text descriptions, and it indicates how descriptions of visual attributes can be generally associated to different people; the other is the\n            <jats:italic toggle=\"yes\">intra-identity<\/jats:italic>\n            variations, which are all those nuisances, e.g., pose, illumination, that can alter the visual appearance of the same textual attributes for a given subject. To address these issues, this article presents a novel TBPS architecture named Mae-Attribute-Relation-Sensitive (MARS), which enhances current state-of-the-art models by introducing two key components: a Visual Reconstruction Loss and an Attribute Loss. The former employs a Masked AutoEncoder trained to reconstruct randomly masked image patches with the aid of the textual description. In doing so the model is encouraged to learn more expressive representations and textual\u2013visual relations in the latent space. The attribute loss, instead, balances the contribution of different types of attributes, defined as adjective\u2013noun chunks of text. This loss ensures that every attribute is taken into consideration in the person retrieval process. Extensive experiments on three commonly used datasets, namely CUHK-PEDES, ICFG-PEDES, and RSTPReid, report performance improvements, with significant gains in the Mean Average Precision (mAP) metric w.r.t. the current state of the art. Code will be available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/ErgastiAlex\/MARS\">https:\/\/github.com\/ErgastiAlex\/MARS<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3721482","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T10:20:56Z","timestamp":1741170056000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["MARS: Paying More Attention to Visual Attributes for Text-Based Person Search"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8110-9714","authenticated-orcid":false,"given":"Alex","family":"Ergasti","sequence":"first","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-4874","authenticated-orcid":false,"given":"Tomaso","family":"Fontanini","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9465-6753","authenticated-orcid":false,"given":"Claudio","family":"Ferrari","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1463-5384","authenticated-orcid":false,"given":"Massimo","family":"Bertozzi","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1211-529X","authenticated-orcid":false,"given":"Andrea","family":"Prati","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612285"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"e_1_3_1_5_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171\u20134186."},{"key":"e_1_3_1_6_2","unstructured":"Zefeng Ding Changxing Ding Zhiyin Shao and Dacheng Tao. 2021. Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv:2107.12666. Retrieved from https:\/\/arxiv.org\/abs\/2107.12666"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Matthew Honnibal Ines Montani Sofie Van Landeghem and Adriane Boyd. 2020. spaCy: Industrial-Strength Natural Language Processing in Python. DOI: 10.5281\/zenodo.1212303","DOI":"10.5281\/zenodo.1212303"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_1_12_2","first-page":"12888","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In Proceedings of the International Conference on Machine Learning. PMLR, 12888\u201312900."},{"key":"e_1_3_1_13_2","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems 34 (2021), 9694\u20139705.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"e_1_3_1_16_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372832"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"e_1_3_1_19_2","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"e_1_3_1_22_2","first-page":"624","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Shu Xiujun","year":"2022","unstructured":"Xiujun Shu, Wei Wen, Haoqian Wu, Keyu Chen, Yiran Song, Ruizhi Qiao, Bo Ren, and Xiao Wang. 2022. See finer, see more: Implicit modality alignment for text-based person retrieval. In Proceedings of the European Conference on Computer Vision. Springer, 624\u2013641."},{"key":"e_1_3_1_23_2","unstructured":"Jintao Sun Zhedong Zheng and Gangyi Ding. 2024. From data deluge to data curation: A filtering-WoRA paradigm for efficient text-based person search. arXiv:2404.10292. Retrieved from https:\/\/arxiv.org\/abs\/2404.10292"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-021-00953-9"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T21:23:08Z","timestamp":1760476988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":31,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3721482"],"URL":"https:\/\/doi.org\/10.1145\/3721482","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"assertion":[{"value":"2024-06-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}