{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:41:16Z","timestamp":1777567276611,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.U23B2013"],"award-info":[{"award-number":["No.U23B2013"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["No.2021JCW-03"],"award-info":[{"award-number":["No.2021JCW-03"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaanxi Provincial Key R&D Program","award":["No.2021KWZ-03, No.2024GX-YBXM-117"],"award-info":[{"award-number":["No.2021KWZ-03, No.2024GX-YBXM-117"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658109","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"579-588","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5171-4548","authenticated-orcid":false,"given":"Ruiqi","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University & Ningbo Institute, Northwestern Polytechnical University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5994-6181","authenticated-orcid":false,"given":"Bingliang","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University & Ningbo Institute, Northwestern Polytechnical University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7142-9734","authenticated-orcid":false,"given":"Wenxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University & Ningbo Institute, Northwestern Polytechnical University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1202-3767","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Honors College, Northwestern Polytechnical University & School of Electronics and Information, Northwestern Polytechnical University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-9132","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University & Ningbo Institute, Northwestern Polytechnical University, Xi'an, Shaanxi, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Exploring Visual Prompts for Adapting Large-Scale Models. arXiv preprint arXiv:2203.17274","author":"Bahng Hyojin","year":"2022","unstructured":"Hyojin Bahng, Ali Jahanian, Swami Sankaranarayanan, and Phillip Isola. 2022. Exploring Visual Prompts for Adapting Large-Scale Models. arXiv preprint arXiv:2203.17274 (2022)."},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3141868"},{"key":"e_1_3_2_1_4_1","first-page":"16664","article-title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","volume":"35","author":"Chen Shoufa","year":"2022","unstructured":"Shoufa Chen, Chongjian GE, Zhan Tong, Jiangliu Wang, Yibing Song, Jue Wang, and Ping Luo. 2022a. AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition. In Proc. Advances in Neural Inf. Process. Syst. , Vol. 35. 16664--16678.","journal-title":"Proc. Advances in Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00065"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/94"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","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. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01161"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. Advances in Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Proc. Advances in Neural Inf. Process. Syst. , Vol. 27."},{"key":"e_1_3_2_1_12_1","unstructured":"Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In Defense of the Triplet Loss for Person Re-Identification. arXiv preprint arXiv:1703.07737 (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19987"},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. Int. Conf. Mach. Learn. 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proc. Int. Conf. Mach. Learn. 448--456."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_16_1","volume-title":"Generalizable Person Re-Identification via Viewpoint Alignment and Fusion. arXiv preprint arXiv:2212.02398","author":"Jiao Bingliang","year":"2022","unstructured":"Bingliang Jiao, Lingqiao Liu, Liying Gao, Guosheng Lin, Ruiqi Wu, Shizhou Zhang, Peng Wang, and Yanning Zhang. 2022a. Generalizable Person Re-Identification via Viewpoint Alignment and Fusion. arXiv preprint arXiv:2212.02398 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_17"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. Advances in Neural Inf. Process. Syst.","author":"Jiao Bingliang","year":"2023","unstructured":"Bingliang Jiao, Lingqiao Liu, Liying Gao, Ruiqi Wu, Guosheng Lin, Peng Wang, and Yanning Zhang. 2023. Toward Re-Identifying Any Animal. In Proc. Advances in Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICA52286.2021.9498199"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237155"},{"key":"e_1_3_2_1_22_1","volume-title":"Class-Aware Modality Mix and Center-Guided Metric Learning for Visible-Thermal Person Re-Identification. In ACM Int. Conf. Multimedia. 889--897","author":"Ling Yongguo","year":"2020","unstructured":"Yongguo Ling, Zhun Zhong, Zhiming Luo, Paolo Rota, Shaozi Li, and Nicu Sebe. 2020. Class-Aware Modality Mix and Center-Guided Metric Learning for Visible-Thermal Person Re-Identification. In ACM Int. Conf. Multimedia. 889--897."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168999"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8565-4_25"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7553002"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25273"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958756"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/s17030605"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_40"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Asian Conference on Computer Vision.","author":"Qian Xuelin","year":"2020","unstructured":"Xuelin Qian, Wenxuan Wang, Li Zhang, Fangrui Zhu, Yanwei Fu, Tao Xiang, Yu-Gang Jiang, and Xiangyang Xue. 2020. Long-term cloth-changing person re-identification. In Proceedings of the Asian Conference on Computer Vision."},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. Int. Conf. Mach. Learn. PMLR, 8748--8763","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 Proc. Int. Conf. Mach. Learn. PMLR, 8748--8763."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"e_1_3_2_1_35_1","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Proc. Advances in Neural Inf. Process. Syst. , Vol. 30, 6000--6010.","journal-title":"Proc. Advances in Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_36_1","volume-title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification. In ACM Int. Conf. Multimedia. 274--282","author":"Wang Guanshuo","year":"2018","unstructured":"Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, and Xi Zhou. 2018. Learning Discriminative Features with Multiple Granularities for Person Re-Identification. In ACM Int. Conf. Multimedia. 274--282."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00372"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00055"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00071"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.575"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107335"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891244"},{"key":"e_1_3_2_1_44_1","volume-title":"Prompting for Multi-Modal Tracking. In ACM Int. Conf. Multimedia. 3492--3500","author":"Yang Jinyu","year":"2022","unstructured":"Jinyu Yang, Zhe Li, Feng Zheng, Ales Leonardis, and Jingkuan Song. 2022. Prompting for Multi-Modal Tracking. In ACM Int. Conf. Multimedia. 3492--3500."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2921454"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_14"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"e_1_3_2_1_48_1","volume-title":"Proc. Int. Conf. Patt. Recogn. 34--39","author":"Yi Dong","unstructured":"Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z. Li. 2014. Deep Metric Learning for Person Re-identification. In Proc. Int. Conf. Patt. Recogn. 34--39."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00345"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2022.9010044"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00720"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163847"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658109","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:50:46Z","timestamp":1755766246000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":54,"alternative-id":["10.1145\/3652583.3658109","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658109","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}