{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:40Z","timestamp":1783737820488,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"name":"Key Research and Development Program of Shaanxi","award":["No.2024GX-YBXM-117"],"award-info":[{"award-number":["No.2024GX-YBXM-117"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101451"],"award-info":[{"award-number":["62101451"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515011394"],"award-info":[{"award-number":["2024A1515011394"]}]},{"name":"Young Talent Fund of Association for Science and Technology in Shaanxi","award":["20240150"],"award-info":[{"award-number":["20240150"]}]},{"name":"China Post-doctoral Science Foundation","award":["2024M754224"],"award-info":[{"award-number":["2024M754224"]}]},{"name":"Shaanxi Post-doctoral Research Project","award":["2024BSHSDZZ088"],"award-info":[{"award-number":["2024BSHSDZZ088"]}]},{"name":"China National Postdoctoral Program for Innovative Talents","award":["BX20230498"],"award-info":[{"award-number":["BX20230498"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754946","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"2997-3006","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Test-Time Adaptation for Text-Based Person Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7997-9930","authenticated-orcid":false,"given":"Kai","family":"Niu","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China and Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6272-2520","authenticated-orcid":false,"given":"Liucun","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3069-9396","authenticated-orcid":false,"given":"Ke","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3214-4797","authenticated-orcid":false,"given":"Qinzi","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Elite Institute of Engineering, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4695-9404","authenticated-orcid":false,"given":"Yue","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Rasa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search. In International Joint Conference on Artificial Intelligence.","author":"Bai Yang","year":"2023","unstructured":"Yang Bai, Min Cao, Daming Gao, Ziqiang Cao, Chen Chen, Zhenfeng Fan, Liqiang Nie, and Min Zhang. 2023. Rasa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search. In International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_2_1","volume-title":"Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval. In ACM International Conference on Multimedia.","author":"Bin Yi","year":"2023","unstructured":"Yi Bin, Haoxuan Li, Yahui Xu, Xing Xu, Yang Yang, and Heng Tao Shen. 2023. Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_3_1","volume-title":"Contrastive Test-Time Adaptation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Chen Dian","year":"2022","unstructured":"Dian Chen, Dequan Wang, Trevor Darrell, and Sayna Ebrahimi. 2022. Contrastive Test-Time Adaptation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3333556"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01063"},{"key":"e_1_3_2_1_6_1","volume-title":"On the Properties of Neural Machine Translation: Encoder-decoder Approaches. In Conference on Empirical Methods in Natural Language Processing Workshops.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the Properties of Neural Machine Translation: Encoder-decoder Approaches. In Conference on Empirical Methods in Natural Language Processing Workshops."},{"key":"e_1_3_2_1_7_1","volume-title":"Similarity Reasoning and Filtration for Image-text Matching. In AAAI Conference on Artificial Intelligence.","author":"Diao Haiwen","year":"2021","unstructured":"Haiwen Diao, Ying Zhang, Lin Ma, and Huchuan Lu. 2021. Similarity Reasoning and Filtration for Image-text Matching. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_8_1","volume-title":"Semantically Self-aligned Network for Text-to-image Part-aware Person Re-identification. arXiv:2107.12666","author":"Ding Zefeng","year":"2021","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 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Giving Text More Imagination Space for Image-text Matching. In ACM International Conference on Multimedia.","author":"Dong Xinfeng","year":"2023","unstructured":"Xinfeng Dong, Longfei Han, Dingwen Zhang, Li Liu, Junwei Han, and Huaxiang Zhang. 2023. Giving Text More Imagination Space for Image-text Matching. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3337972"},{"key":"e_1_3_2_1_11_1","volume-title":"Axm-net: Implicit Cross-modal Feature Alignment for Person Re-identification. In AAAI Conference on Artificial Intelligence.","author":"Farooq Ammarah","year":"2022","unstructured":"Ammarah Farooq, Muhammad Awais, Josef Kittler, and Syed Safwan Khalid. 2022. Axm-net: Implicit Cross-modal Feature Alignment for Person Re-identification. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_12_1","volume-title":"Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning. In IEEE\/CVF International Conference on Computer Vision.","author":"Feng Chun-Mei","year":"2023","unstructured":"Chun-Mei Feng, Kai Yu, Yong Liu, Salman Khan, and Wangmeng Zuo. 2023. Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning. In IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_13_1","first-page":"972","volume-title":"Science","volume":"315","author":"Frey Brendan J","year":"2007","unstructured":"Brendan J Frey and Delbert Dueck. 2007. Clustering by Passing Messages between Data Points. Science, Vol. 315, 5814 (2007), 972-976."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1975.1055330"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273719"},{"key":"e_1_3_2_1_17_1","volume-title":"Clothes-changing Person Re-identification with RGB Modality Only. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Gu Xinqian","year":"2022","unstructured":"Xinqian Gu, Hong Chang, Bingpeng Ma, Shutao Bai, Shiguang Shan, and Xilin Chen. 2022. Clothes-changing Person Re-identification with RGB Modality Only. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19963"},{"key":"e_1_3_2_1_19_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_20_1","volume-title":"Transreid: Transformer-based Object Re-identification. In IEEE\/CVF International Conference on Computer Vision.","author":"He Shuting","year":"2021","unstructured":"Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, and Wei Jiang. 2021. Transreid: Transformer-based Object Re-identification. In IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_21_1","volume-title":"Cross-modal Implicit Relation Reasoning and Aligning for Text-to-image Person Retrieval. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Jiang Ding","year":"2023","unstructured":"Ding Jiang and Mang Ye. 2023. Cross-modal Implicit Relation Reasoning and Aligning for Text-to-image Person Retrieval. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_22_1","volume-title":"Efficient Test-Time Adaptation of Vision-Language Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Karmanov Adilbek","year":"2024","unstructured":"Adilbek Karmanov, Dayan Guan, Shijian Lu, Abdulmotaleb El Saddik, and Eric Xing. 2024. Efficient Test-Time Adaptation of Vision-Language Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_23_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations.","author":"Lee Jonghyun","year":"2024","unstructured":"Jonghyun Lee, Dahuin Jung, Saehyung Lee, Junsung Park, Juhyeon Shin, Uiwon Hwang, and Sungroh Yoon. 2024. Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","volume-title":"Test-time Adaptation for Cross-modal Retrieval with Query Shift. In International Conference on Learning Representations.","author":"Li Haobin","year":"2025","unstructured":"Haobin Li, Peng Hu, Qianjun Zhang, Xi Peng, Xiting Liu, and Mouxing Yang. 2025. Test-time Adaptation for Cross-modal Retrieval with Query Shift. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","volume-title":"Adaptive Uncertainty-based Learning for Text-based Person Retrieval. In AAAI Conference on Artificial Intelligence.","author":"Li Shenshen","year":"2024","unstructured":"Shenshen Li, Chen He, Xing Xu, Fumin Shen, Yang Yang, and Heng Tao Shen. 2024. Adaptive Uncertainty-based Learning for Text-based Person Retrieval. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_28_1","volume-title":"Person Search with Natural Language Description. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Li Shuang","year":"2017","unstructured":"Shuang Li, Tong Xiao, Hongsheng Li, Bolei Zhou, Dayu Yue, and Xiaogang Wang. 2017. Person Search with Natural Language Description. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_29_1","volume-title":"Deep Cross-modal Evidential Learning for Text-based Person Retrieval. In ACM International Conference on Multimedia.","author":"Li Shenshen","year":"2023","unstructured":"Shenshen Li, Xing Xu, Yang Yang, Fumin Shen, Yijun Mo, Yujie Li, and Heng Tao Shen. 2023b. Deep Cross-modal Evidential Learning for Text-based Person Retrieval. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_30_1","volume-title":"Towards Deconfounded Image-Text Matching with Causal Inference. In ACM International Conference on Multimedia.","author":"Li Wenhui","year":"2023","unstructured":"Wenhui Li, Xinqi Su, Dan Song, Lanjun Wang, Kun Zhang, and An-An Liu. 2023a. Towards Deconfounded Image-Text Matching with Causal Inference. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_31_1","volume-title":"Source Hypothesis Transfer for Unsupervised Domain Adaptation. In International Conference on Machine Learning.","author":"Liang Jian","year":"2020","unstructured":"Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20068"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262130"},{"key":"e_1_3_2_1_35_1","volume-title":"Some Methods for Classification and Analysis of Multivariate Observations. In Berkeley Symposium on Mathematical Statistics and Probability.","author":"MacQueen James","year":"1967","unstructured":"James MacQueen. 1967. Some Methods for Classification and Analysis of Multivariate Observations. In Berkeley Symposium on Mathematical Statistics and Probability."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372832"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_38_1","volume-title":"An Overview of Text-based Person Search: Recent Advances and Future Directions","author":"Niu Kai","year":"2024","unstructured":"Kai Niu, Yanyi Liu, Yuzhou Long, Yan Huang, Liang Wang, and Yanning Zhang. 2024b. An Overview of Text-based Person Search: Recent Advances and Future Directions. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning.","author":"Niu Shuaicheng","year":"2022","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, and Mingkui Tan. 2022. Efficient Test-time Model Adaptation without Forgetting. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_40_1","volume-title":"Towards Stable Test-time Adaptation in Dynamic Wild World. In International Conference on Learning Representations.","author":"Niu Shuaicheng","year":"2023","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, and Mingkui Tan. 2023. Towards Stable Test-time Adaptation in Dynamic Wild World. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_41_1","volume-title":"Noisy-correspondence Learning for Text-to-image Person Re-identification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Qin Yang","year":"2024","unstructured":"Yang Qin, Yingke Chen, Dezhong Peng, Xi Peng, Joey Tianyi Zhou, and Peng Hu. 2024. Noisy-correspondence Learning for Text-to-image Person Re-identification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_42_1","volume-title":"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 International Conference on Machine Learning."},{"key":"e_1_3_2_1_43_1","first-page":"14274","article-title":"Test-time Prompt Tuning for Zero-shot Generalization in Vision-language Models","volume":"35","author":"Shu Manli","year":"2022","unstructured":"Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, and Chaowei Xiao. 2022a. Test-time Prompt Tuning for Zero-shot Generalization in Vision-language Models. Neural Information Processing Systems, Vol. 35 (2022), 14274-14289.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","volume-title":"More: Implicit Modality Alignment for Text-based Person Retrieval. In European Conference on Computer Vision Workshops.","author":"Shu Xiujun","year":"2022","unstructured":"Xiujun Shu, Wei Wen, Haoqian Wu, Keyu Chen, Yiran Song, Ruizhi Qiao, Bo Ren, and Xiao Wang. 2022b. See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval. In European Conference on Computer Vision Workshops."},{"key":"e_1_3_2_1_45_1","volume-title":"Adaptive Background Mixture Models for Real-time Tracking. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition.","author":"Stauffer Chris","year":"1999","unstructured":"Chris Stauffer and W Eric L Grimson. 1999. Adaptive Background Mixture Models for Real-time Tracking. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_46_1","volume-title":"MACA: Memory-aided Coarse-to-fine Alignment for Text-based Person Search. In ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Su Liangxu","year":"2024","unstructured":"Liangxu Su, Rong Quan, Zhiyuan Qi, and Jie Qin. 2024. MACA: Memory-aided Coarse-to-fine Alignment for Text-based Person Search. In ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3322659"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Learning Representations.","author":"Wang Dequan","year":"2021","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2021. Tent: Fully Test-time Adaptation by Entropy Minimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_50_1","volume-title":"Nformer: Robust Person Re-identification with Neighbor Transformer. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Wang Haochen","year":"2022","unstructured":"Haochen Wang, Jiayi Shen, Yongtuo Liu, Yan Gao, and Efstratios Gavves. 2022b. Nformer: Robust Person Re-identification with Neighbor Transformer. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_51_1","volume-title":"ACM International Conference on Multimedia.","author":"Wang Junsheng","year":"2022","unstructured":"Junsheng Wang, Tiantian Gong, Zhixiong Zeng, Changchang Sun, and Yan Yan. 2022a. C3CMR: Cross-Modality Cross-Instance Contrastive Learning for Cross-Media Retrieval. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_52_1","volume-title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval. In ACM International Conference on Multimedia.","author":"Wang Yabing","year":"2024","unstructured":"Yabing Wang, Le Wang, Qiang Zhou, Zhibin Wang, Hao Li, Gang Hua, and Wei Tang. 2024. Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_53_1","volume-title":"From Denoising Training To Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation. In IEEE\/CVF Winter Conference on Applications of Computer Vision.","author":"Wen Ruxue","year":"2024","unstructured":"Ruxue Wen, Hangjie Yuan, Dong Ni, Wenbo Xiao, and Yaoyao Wu. 2024. From Denoising Training To Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation. In IEEE\/CVF Winter Conference on Applications of Computer Vision."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"e_1_3_2_1_55_1","volume-title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-attribute and Language Search Benchmark. In ACM International Conference on Multimedia.","author":"Yang Shuyu","year":"2023","unstructured":"Shuyu Yang, Yinan Zhou, Zhedong Zheng, Yaxiong Wang, Li Zhu, and Yujiao Wu. 2023. Towards Unified Text-based Person Retrieval: A Large-scale Multi-attribute and Language Search Benchmark. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611919"},{"key":"e_1_3_2_1_57_1","volume-title":"Negative-aware Attention Framework for Image-text Matching. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Zhang Kun","year":"2022","unstructured":"Kun Zhang, Zhendong Mao, Quan Wang, and Yongdong Zhang. 2022b. Negative-aware Attention Framework for Image-text Matching. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_58_1","first-page":"38629","article-title":"Memo: Test Time Robustness via Adaptation and Augmentation","volume":"35","author":"Zhang Marvin","year":"2022","unstructured":"Marvin Zhang, Sergey Levine, and Chelsea Finn. 2022a. Memo: Test Time Robustness via Adaptation and Augmentation. Neural Information Processing Systems, Vol. 35 (2022), 38629-38642.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","volume-title":"Weakly Supervised Text-based Person Re-identification. In IEEE\/CVF International Conference on Computer Vision.","author":"Zhao Shizhen","year":"2021","unstructured":"Shizhen Zhao, Changxin Gao, Yuanjie Shao, Wei-Shi Zheng, and Nong Sang. 2021. Weakly Supervised Text-based Person Re-identification. In IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_60_1","volume-title":"Group-aware Label Transfer for Domain Adaptive Person Re-identification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Zheng Kecheng","year":"2021","unstructured":"Kecheng Zheng, Wu Liu, Lingxiao He, Tao Mei, Jiebo Luo, and Zheng-Jun Zha. 2021a. Group-aware Label Transfer for Domain Adaptive Person Re-identification. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00826"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_63_1","volume-title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval. In ACM International Conference on Multimedia.","author":"Zhu Aichun","year":"2021","unstructured":"Aichun Zhu, Zijie Wang, Yifeng Li, Xili Wan, Jing Jin, Tian Wang, Fangqiang Hu, and Gang Hua. 2021. DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval. In ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_64_1","volume-title":"UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Zuo Jialong","year":"2024","unstructured":"Jialong Zuo, Hanyu Zhou, Ying Nie, Feng Zhang, Tianyu Guo, Nong Sang, Yunhe Wang, and Changxin Gao. 2024. UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:16:56Z","timestamp":1765340216000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754946"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3754946","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754946","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}