{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:57Z","timestamp":1776890037418,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T00:00:00Z","timestamp":1629763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["No. U19B2037"],"award-info":[{"award-number":["No. U19B2037"]}]},{"name":"the Ministry of Science and Technology of China","award":["No. 2020AAA0106900"],"award-info":[{"award-number":["No. 2020AAA0106900"]}]},{"name":"the Open Projects Program of National Laboratory of Pattern Recognition","award":["No. 202100028"],"award-info":[{"award-number":["No. 202100028"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,24]]},"DOI":"10.1145\/3460426.3463652","type":"proceedings-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T22:50:29Z","timestamp":1630536629000},"page":"118-126","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Text-Guided Visual Feature Refinement for Text-Based Person Search"],"prefix":"10.1145","author":[{"given":"Liying","family":"Gao","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}]},{"given":"Kai","family":"Niu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}]},{"given":"Zehong","family":"Ma","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}]},{"given":"Bingliang","family":"Jiao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}]},{"given":"Tonghao","family":"Tan","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}]}],"member":"320","published-online":{"date-parts":[[2021,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_4"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00336"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 24th International Conference on Artificial Intelligence. 3402--3408","author":"Chen YingCong","year":"2015","unstructured":"YingCong Chen , WeiShi Zheng , and Jianhuang Lai . 2015 . Mirror Representation for Modeling View-Specific Transform in Person Re-Identification . In Proceedings of the 24th International Conference on Artificial Intelligence. 3402--3408 . YingCong Chen, WeiShi Zheng, and Jianhuang Lai. 2015. Mirror Representation for Modeling View-Specific Transform in Person Re-Identification. In Proceedings of the 24th International Conference on Artificial Intelligence. 3402--3408."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","volume-title":"FD-GAN: Pose-guided feature distilling GAN for robust person re-identification. arXiv preprint arXiv:1810.02936","author":"Ge Yixiao","year":"2018","unstructured":"Yixiao Ge , Zhuowan Li , Haiyu Zhao , Guojun Yin , Shuai Yi , Xiaogang Wang , and Hongsheng Li. 2018. FD-GAN: Pose-guided feature distilling GAN for robust person re-identification. arXiv preprint arXiv:1810.02936 ( 2018 ). Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, and Hongsheng Li. 2018. FD-GAN: Pose-guided feature distilling GAN for robust person re-identification. arXiv preprint arXiv:1810.02936 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 ( 2017 ). Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 451--466","author":"Huijuan Xu","year":"2016","unstructured":"Xu Huijuan and Saenko Kate . 2016 . Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering . In Proceedings of the European Conference on Computer Vision (ECCV). 451--466 . Xu Huijuan and Saenko Kate. 2016. Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering. In Proceedings of the European Conference on Computer Vision (ECCV). 451--466."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_11_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1239--1248","author":"Li Zhang","year":"2016","unstructured":"Zhang Li , Tao Xiang , and Shaogang Gong . 2016 . Learning a Discriminative Null Space for Person Re-Identification . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1239--1248 . Zhang Li, Tao Xiang, and Shaogang Gong. 2016. Learning a Discriminative Null Space for Person Re-Identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1239--1248."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1307--1315","author":"Licheng Yu","year":"2018","unstructured":"Yu Licheng , Lin Zhe , Shen Xiaohui , Yang Jimei , Lu Xin , Bansal Mohit , and Berg Tamara L. 2018 . MAttNet: Modular Attention Network for Referring Expression Comprehension . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1307--1315 . Yu Licheng, Lin Zhe, Shen Xiaohui, Yang Jimei, Lu Xin, Bansal Mohit, and Berg Tamara L. 2018. MAttNet: Modular Attention Network for Referring Expression Comprehension. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1307--1315."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00431"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 858--877","author":"Das Abir","unstructured":"Martinel, Niki, Abir Das , Christian Micheloni , and Amit K . Roy-Chowdhury. 2016. Temporal Model Adaptation for Person Re-Identification . In Proceedings of the European Conference on Computer Vision (ECCV). 858--877 . Martinel, Niki, Abir Das, Christian Micheloni, and Amit K. Roy-Chowdhury. 2016. Temporal Model Adaptation for Person Re-Identification. In Proceedings of the European Conference on Computer Vision (ECCV). 858--877."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00051"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_10"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_25"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 26th ACM international conference on Multimedia. 274--282","author":"Yuan Yufeng","year":"2018","unstructured":"GuanshuoWang, Yufeng Yuan , Xiong Chen , Jiwei Li , and Xi Zhou . 2018 . Learning discriminative features with multiple granularities for person re-identification . In Proceedings of the 26th ACM international conference on Multimedia. 274--282 . GuanshuoWang, Yufeng Yuan, Xiong Chen, Jiwei Li, and Xi Zhou. 2018. Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 26th ACM international conference on Multimedia. 274--282."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1960--1968","author":"Wang Peng","unstructured":"Peng Wang , Qi Wu , Jiewei Cao , Chunhua Shen , Lianli Gao , and Anton van den Hengel. 2019. Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1960--1968 . Peng Wang, Qi Wu, Jiewei Cao, Chunhua Shen, Lianli Gao, and Anton van den Hengel. 2019. Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1960--1968."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_29_1","volume-title":"Hoi","author":"Ye Mang","year":"2021","unstructured":"Mang Ye , Jianbing Shen , Gaojie Lin , Tao Xiang , Ling Shao , and Steven C.H . Hoi . 2021 . Deep Learning for Person Re-identification: A Survey and Outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2021), 1--1. Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, and Steven C.H. Hoi. 2021. Deep Learning for Person Re-identification: A Survey and Outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021), 1--1."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"},{"key":"e_1_3_2_1_32_1","volume-title":"Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535","author":"Zheng Zhedong","year":"2017","unstructured":"Zhedong Zheng , Liang Zheng , Michael Garrett , Yi Yang , and Yi-Dong Shen . 2017. Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535 ( 2017 ). Zhedong Zheng, Liang Zheng, Michael Garrett, Yi Yang, and Yi-Dong Shen. 2017. Dual-path convolutional image-text embedding with instance loss. arXiv preprint arXiv:1711.05535 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12241"}],"event":{"name":"ICMR '21: International Conference on Multimedia Retrieval","location":"Taipei Taiwan","acronym":"ICMR '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2021 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463652","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460426.3463652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:04Z","timestamp":1750191424000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463652"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,24]]},"references-count":33,"alternative-id":["10.1145\/3460426.3463652","10.1145\/3460426"],"URL":"https:\/\/doi.org\/10.1145\/3460426.3463652","relation":{},"subject":[],"published":{"date-parts":[[2021,8,24]]},"assertion":[{"value":"2021-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}