{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:17:58Z","timestamp":1783153078592,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"NSFC","award":["62272416"],"award-info":[{"award-number":["62272416"]}]},{"name":"National Education Sciences Planning Project","award":["BCA240048"],"award-info":[{"award-number":["BCA240048"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792417","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T12:38:33Z","timestamp":1777293513000},"page":"7247-7258","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BHGap: A Deep Iterative Prompting and Multi-stage Alignment Framework for Dynamic Facial Expression Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7647-4454","authenticated-orcid":false,"given":"Yichi","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6776-5108","authenticated-orcid":false,"given":"Yunqi","family":"Han","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1375-8131","authenticated-orcid":false,"given":"Jiayue","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0243-3613","authenticated-orcid":false,"given":"Liangyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01834"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680827"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3453443"},{"key":"e_1_3_2_1_6_1","volume-title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection. arXiv preprint arXiv:2505.02331","author":"Cheng Hao","year":"2025","unstructured":"Hao Cheng, Zhiwei Zhao, Yichao He, Zhenzhen Hu, Jia Li, Meng Wang, and Richang Hong. 2025. VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection. arXiv preprint arXiv:2505.02331 (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00470"},{"key":"e_1_3_2_1_8_1","volume-title":"Learning from heterogeneity: Generalizing dynamic facial expression recognition via distributionally robust optimization. arXiv preprint arXiv:2507.15765","author":"Cui Feng-Qi","year":"2025","unstructured":"Feng-Qi Cui, Anyang Tong, Jinyang Huang, Jie Zhang, Dan Guo, Zhi Liu, and Meng Wang. 2025. Learning from heterogeneity: Generalizing dynamic facial expression recognition via distributionally robust optimization. arXiv preprint arXiv:2507.15765 (2025)."},{"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\/FG59268.2024.10581982"},{"key":"e_1_3_2_1_11_1","volume-title":"Emotion detection and analysis on social media. arXiv preprint arXiv:1901.08458","author":"Gaind Bharat","year":"2019","unstructured":"Bharat Gaind, Varun Syal, and Sneha Padgalwar. 2019. Emotion detection and analysis on social media. arXiv preprint arXiv:1901.08458 (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"Hankel low-rank approximation and completion in time series analysis and forecasting: a brief review. arXiv preprint arXiv:2206.05103","author":"Gillard Jonathan","year":"2022","unstructured":"Jonathan Gillard and Konstantin Usevich. 2022. Hankel low-rank approximation and completion in time series analysis and forecasting: a brief review. arXiv preprint arXiv:2206.05103 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2188410"},{"key":"e_1_3_2_1_14_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3285777"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 5769 - 5779","author":"Gulrajani Ishaan","year":"2017","unstructured":"Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C Courville. 2017. Improved training of wasserstein gans. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 5769 - 5779."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3006392"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602351"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25077"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687508"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681708"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548190"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510622"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00630"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 28th International Conference on Machine Learning. 689-696","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, Andrew Y Ng, et al., 2011. Multimodal deep learning. In Proceedings of the 28th International Conference on Machine Learning. 689-696."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning. 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 Proceedings of the 38th International Conference on Machine Learning. 8748-8763."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_21"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612365"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102382"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01790"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00854"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01869"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054229"},{"key":"e_1_3_2_1_39_1","volume-title":"Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250","author":"Zadeh Amir","year":"2017","unstructured":"Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"e_1_3_2_1_42_1","volume-title":"Prompting visual-language models for dynamic facial expression recognition. arXiv preprint arXiv:2308.13382","author":"Zhao Zengqun","year":"2023","unstructured":"Zengqun Zhao and Ioannis Patras. 2023. Prompting visual-language models for dynamic facial expression recognition. arXiv preprint arXiv:2308.13382 (2023)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:38:31Z","timestamp":1783150711000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":42,"alternative-id":["10.1145\/3774904.3792417","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792417","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}