{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hierarchical-gumbel-attention-network-for","title":"Hierarchical Gumbel Attention Network for Text-based Person Search","arxiv_id":null,"date":"2020-10-10","proceeding":null,"authors":["Kecheng Zheng","Wu Liu","Jiawei Liu","Zheng-Jun Zha","Tao Mei"],"abstract":"Text-based person search aims to retrieve the pedestrian images that best match a given textual description from gallery images. Previous methods utilize the soft-attention mechanism to infer the semantic alignments between the regions of image and the corresponding words in sentence. However, these methods may fuse the irrelevant multi-modality features together which cause matching redundancy problem. In this work, we propose a novel hi\u0002erarchical Gumbel attention network for text-based person search via Gumbel top-k re-parameterization algorithm. Specifically, it adaptively selects the strong semantically relevant image regions and words/phrases from images and texts for precise alignment and similarity calculation. This hard selection strategy is able to fuse the strong-relevant multi-modality features for alleviating the problem of matching redundancy. Meanwhile, a Gumbel top-k re\u0002parameterization algorithm is designed as a low-variance, unbiased gradient estimator to handle the discreteness problem of hard atten\u0002tion mechanism by an end-to-end manner. Moreover, a hierarchical adaptive matching strategy is employed by the model from three different granularities, i.e., word-level, phrase-level, and sentence\u0002level, towards fine-grained matching. Extensive experimental re\u0002sults demonstrate the state-of-the-art performance. Compared the existed best method, we achieve the 8.24% Rank-1 and 7.6% mAP relative improvements in the text-to-image retrieval task, and 5.58% Rank-1 and 6.3% mAP relative improvements in the image-to-text retrieval task on CUHK-PEDES dataset, respectively","url_abs":"https://www.researchgate.net/publication/346192190_Hierarchical_Gumbel_Attention_Network_for_Text-based_Person_Search","url_pdf":"https://www.researchgate.net/publication/346192190_Hierarchical_Gumbel_Attention_Network_for_Text-based_Person_Search","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"person-search","task_name":"Person Search"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"nlp-based-person-retrival","task_name":"Text based Person Retrieval"},{"task_slug":"text-based-person-search","task_name":"Text based Person Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/nlp-based-person-retrival-on-cuhk-pedes","task":"Text based Person Retrieval","dataset":"CUHK-PEDES","model":"HGAN","rank_in_archive_order":14,"of":21,"metrics":{"R@1":"59.00","R@10":"86.62","R@5":"79.49"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}