{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T04:30:30Z","timestamp":1772771430328,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["NSFC62071292"],"award-info":[{"award-number":["NSFC62071292"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612869","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"9581-9585","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8565-3857","authenticated-orcid":false,"given":"Zhigang","family":"Chang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4399-2973","authenticated-orcid":false,"given":"Weitai","family":"Hu","sequence":"additional","affiliation":[{"name":"Du Xiaoman Financial, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0833-8204","authenticated-orcid":false,"given":"Qing","family":"Yang","sequence":"additional","affiliation":[{"name":"Du Xiaoman Financial, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5060-0210","authenticated-orcid":false,"given":"Shibao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675368"},{"key":"e_1_3_2_1_3_1","volume-title":"Soyeon Choe, Chiheon Ham, Sunghwan Jung, Bong-Jin Lee, and Icksang Han.","author":"Chung Joon Son","year":"2020","unstructured":"Joon Son Chung, Jaesung Huh, Seongkyu Mun, Minjae Lee, Hee Soo Heo, Soyeon Choe, Chiheon Ham, Sunghwan Jung, Bong-Jin Lee, and Icksang Han. 2020. In defence of metric learning for speaker recognition. arXiv preprint arXiv:2003.11982 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_10"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_8_1","first-page":"378","article-title":"Recurrent video restoration transformer with guided deformable attention","volume":"35","author":"Liang Jingyun","year":"2022","unstructured":"Jingyun Liang, Yuchen Fan, Xiaoyu Xiang, Rakesh Ranjan, Eddy Ilg, Simon Green, Jiezhang Cao, Kai Zhang, Radu Timofte, and Luc V Gool. 2022. Recurrent video restoration transformer with guided deformable attention. Advances in Neural Information Processing Systems, Vol. 35 (2022), 378--393.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"e_1_3_2_1_10_1","volume-title":"ReactFace: 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, Linlin Shen, and Hatice Gunes. 2023. ReactFace: Multiple Appropriate Facial Reaction Generation in Dyadic Interactions. arXiv preprint arXiv:2305.15748 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Pascal Paysan Reinhard Knothe Brian Amberg Sami Romdhani and Thomas Vetter. 2009. A 3D face model for pose and illumination invariant face recognition. In 2009 sixth IEEE international conference on advanced video and signal based surveillance. Ieee 296--301.","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475460"},{"key":"e_1_3_2_1_16_1","volume-title":"Learning person-specific cognition from facial reactions for automatic personality recognition","author":"Song Siyang","year":"2022","unstructured":"Siyang Song, Zilong Shao, Shashank Jaiswal, Linlin Shen, Michel Valstar, and Hatice Gunes. 2022. Learning person-specific cognition from facial reactions for automatic personality recognition. IEEE Transactions on Affective Computing (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Explicitly controllable 3d-aware portrait generation. arXiv preprint arXiv:2209.05434","author":"Tang Junshu","year":"2022","unstructured":"Junshu Tang, Bo Zhang, Binxin Yang, Ting Zhang, Dong Chen, Lizhuang Ma, and Fang Wen. 2022. Explicitly controllable 3d-aware portrait generation. arXiv preprint arXiv:2209.05434 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_2_1_19_1","unstructured":"Mohan Zhou Yalong Bai Wei Zhang Ting Yao and Tiejun Zhao. 2023 a. Interactive Conversational Head Generation. arxiv: 2307.02090 [cs.CV]"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_8"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095084"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612869","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:34Z","timestamp":1755820894000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":22,"alternative-id":["10.1145\/3581783.3612869","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612869","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}