{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:15:51Z","timestamp":1765307751273,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762246","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"13992-13996","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multiple Appropriate Facial Reaction Generation Based on Multi-View Transformation of Speaker Video"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9298-7950","authenticated-orcid":false,"given":"Jiajian","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Information Science and Technology, Great Bay University, Dongguan, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6505-3304","authenticated-orcid":false,"given":"Zitong","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Information Science and Technology, Great Bay University, Dongguan, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887743"},{"key":"e_1_3_2_1_2_1","volume-title":"Reactdiff: Latent diffusion for facial reaction generation. Neural Networks, page 107596","author":"Li Jiaming","year":"2025","unstructured":"Jiaming Li, Sheng Wang, Xin Wang, Yitao Zhu, Honglin Xiong, Zixu Zhuang, and Qian Wang. Reactdiff: Latent diffusion for facial reaction generation. Neural Networks, page 107596, 2025."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32159"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2021.1898851"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2022.102819"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612860"},{"key":"e_1_3_2_1_7_1","volume-title":"Reactface: Online multiple appropriate facial reaction generation in dyadic interactions. arXiv preprint arXiv:2305.15748","author":"Luo Cheng","year":"2023","unstructured":"Cheng Luo, Siyang Song, Weicheng Xie, Micol Spitale, Zongyuan Ge, Linlin Shen, and Hatice Gunes. Reactface: Online multiple appropriate facial reaction generation in dyadic interactions. arXiv preprint arXiv:2305.15748, 2023."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612854"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612865"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581978"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582013"},{"key":"e_1_3_2_1_12_1","first-page":"233","volume-title":"International Conference on Pattern Recognition","author":"Nguyen Minh-Duc","year":"2024","unstructured":"Minh-Duc Nguyen, Hyung-Jeong Yang, Soo-Hyung Kim, Ji-Eun Shin, and Seung-Won Kim. Latent behavior diffusion for sequential reaction generation in dyadic setting. In International Conference on Pattern Recognition, pages 233-248. Springer, 2024."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680752"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00441"},{"key":"e_1_3_2_1_15_1","volume-title":"Multiple appropriate facial reaction generation in dyadic interaction settings: What, why and how? arXiv preprint arXiv:2302.06514","author":"Song Siyang","year":"2023","unstructured":"Siyang Song, Micol Spitale, Yiming Luo, Batuhan Bal, and Hatice Gunes. Multiple appropriate facial reaction generation in dyadic interaction settings: What, why and how? arXiv preprint arXiv:2302.06514, 2023."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612832"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136780"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581935"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581901"},{"key":"e_1_3_2_1_21_1","volume-title":"React 2025: the third multiple appropriate facial reaction generation challenge. arXiv preprint arXiv:2505.17223","author":"Song Siyang","year":"2025","unstructured":"Siyang Song, Micol Spitale, Xiangyu Kong, Hengde Zhu, Cheng Luo, Cristina Palmero, German Barquero, Sergio Escalera, Michel Valstar, Mohamed Daoudi, et al. React 2025: the third multiple appropriate facial reaction generation challenge. arXiv preprint arXiv:2505.17223, 2025."},{"key":"e_1_3_2_1_22_1","volume-title":"Reversible graph neural network-based reaction distribution learning for multiple appropriate facial reactions generation. arXiv preprint arXiv:2305.15270","author":"Xu Tong","year":"2023","unstructured":"Tong Xu, Micol Spitale, Hao Tang, Lu Liu, Hatice Gunes, and Siyang Song. Reversible graph neural network-based reaction distribution learning for multiple appropriate facial reactions generation. arXiv preprint arXiv:2305.15270, 2023."},{"key":"e_1_3_2_1_23_1","first-page":"1","article-title":"Investigating and enhancing audio-visual understanding in large language models","author":"Ye Qilang","year":"2025","unstructured":"Qilang Ye, Zitong Yu, Rui Shao, Yawen Cui, Xiangui Kang, Xin Liu, Philip Torr, and Xiaochun Cao. Cat: Investigating and enhancing audio-visual understanding in large language models. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1-18, 2025.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence, pages"},{"key":"e_1_3_2_1_24_1","volume-title":"Feallm: Advancing facial emotion analysis in multimodal large language models with emotional synergy and reasoning. arXiv preprint arXiv:2505.13419","author":"Hu Zhuozhao","year":"2025","unstructured":"Zhuozhao Hu, Kaishen Yuan, Xin Liu, Zitong Yu, Yuan Zong, Jingang Shi, Huanjing Yue, and Jingyu Yang. Feallm: Advancing facial emotion analysis in multimodal large language models with emotional synergy and reasoning. arXiv preprint arXiv:2505.13419, 2025."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00415"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01758-1"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3762246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:12:40Z","timestamp":1765307560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":26,"alternative-id":["10.1145\/3746027.3762246","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762246","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"}}]}}