{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:10:20Z","timestamp":1784013020837,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2023AFB572"],"award-info":[{"award-number":["2023AFB572"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100020725","name":"Hubei Key Laboratory of Intelligent Geo-Information Processing","doi-asserted-by":"publisher","award":["KLIGIP-2022-B10"],"award-info":[{"award-number":["KLIGIP-2022-B10"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100020725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["62076227"],"award-info":[{"award-number":["62076227"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681583","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"5722-5731","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1913-0089","authenticated-orcid":false,"given":"Yuanyuan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1094-934X","authenticated-orcid":false,"given":"Yuxuan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1360-7631","authenticated-orcid":false,"given":"Shuyang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, China University of Geosciences (Wuhan), Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3180-0484","authenticated-orcid":false,"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2518-9977","authenticated-orcid":false,"given":"Zijing","family":"Chen","sequence":"additional","affiliation":[{"name":"Cisco - La Trobe Centre for Artificial Intelligence and Internet of Things, La Trobe University, Flora Hill, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-8975","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Cisco - La Trobe Centre for Artificial Intelligence and Internet of Things, La Trobe University, Flora Hill, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_2_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_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01310"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3141400"},{"key":"e_1_3_2_2_6_1","volume-title":"Facial expression recognition for human computer interaction. New Trends in Computational Vision and Bio-inspired Computing: Selected works presented at the ICCVBIC","author":"Chattopadhyay Joyati","year":"2018","unstructured":"Joyati Chattopadhyay, Souvik Kundu, Arpita Chakraborty, and Jyoti Sekhar Banerjee. 2020. Facial expression recognition for human computer interaction. New Trends in Computational Vision and Bio-inspired Computing: Selected works presented at the ICCVBIC 2018, Coimbatore, India (2020), 1181--1192."},{"key":"e_1_3_2_2_7_1","first-page":"8065","article-title":"Adversarial reciprocal points learning for open set recognition","volume":"44","author":"Chen Guangyao","year":"2021","unstructured":"Guangyao Chen, Peixi Peng, Xiangqian Wang, and Yonghong Tian. 2021. Adversarial reciprocal points learning for open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 11 (2021), 8065--8081.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings, Part III 16","author":"Chen Guangyao","year":"2020","unstructured":"Guangyao Chen, Limeng Qiao, Yemin Shi, Peixi Peng, Jia Li, Tiejun Huang, Shiliang Pu, and Yonghong Tian. 2020. Learning open set network with discriminative reciprocal points. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part III 16. Springer, 507--522."},{"key":"e_1_3_2_2_9_1","volume-title":"On Catastrophic Inheritance of Large Foundation Models. arXiv preprint arXiv:2402.01909","author":"Chen Hao","year":"2024","unstructured":"Hao Chen, Bhiksha Raj, Xing Xie, and Jindong Wang. 2024. On Catastrophic Inheritance of Large Foundation Models. arXiv preprint arXiv:2402.01909 (2024)."},{"key":"e_1_3_2_2_10_1","volume-title":"Learning with Noisy Foundation Models. arXiv preprint arXiv:2403.06869","author":"Chen Hao","year":"2024","unstructured":"Hao Chen, Jindong Wang, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, and Bhiksha Raj. 2024. Learning with Noisy Foundation Models. arXiv preprint arXiv:2403.06869 (2024)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"e_1_3_2_2_13_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_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3252275"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200384"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2695999"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00085"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548021"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.062"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.03.062"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109368"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264992"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_21"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_38"},{"key":"e_1_3_2_2_29_1","volume-title":"International conference on machine learning. 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 International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_30_1","volume-title":"A 2 Pt: Anti-Associative Prompt Tuning for Open Set Visual Recognition","author":"Ren Hairui","year":"2023","unstructured":"Hairui Ren, Fan Tang, Xingjia Pan, Juan Cao, Weiming Dong, Zhiwen Lin, Ke Yan, and Changsheng Xu. 2023. A 2 Pt: Anti-Associative Prompt Tuning for Open Set Visual Recognition. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_2_31_1","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, SM Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal few-shot learning with frozen language models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 200--212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01857"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756565"},{"key":"e_1_3_2_2_36_1","volume-title":"Unleashing the power of visual prompting at the pixel level. arXiv preprint arXiv:2212.10556","author":"Wu Junyang","year":"2022","unstructured":"Junyang Wu, Xianhang Li, Chen Wei, Huiyu Wang, Alan Yuille, Yuyin Zhou, and Cihang Xie. 2022. Unleashing the power of visual prompting at the pixel level. arXiv preprint arXiv:2212.10556 (2022)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01107"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01421"},{"key":"e_1_3_2_2_41_1","volume-title":"Open-Set Facial Expression Recognition. arXiv preprint arXiv:2401.12507","author":"Zhang Yuhang","year":"2024","unstructured":"Yuhang Zhang, Yue Yao, Xuannan Liu, Lixiong Qin, Wenjing Wang, and Weihong Deng. 2024. Open-Set Facial Expression Recognition. arXiv preprint arXiv:2401.12507 (2024)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00098"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612546"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681583","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:48Z","timestamp":1750295868000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681583","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681583","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}