{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:46:17Z","timestamp":1767033977245,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":58,"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":[{"name":"Science and Technology Project of Inner Mongolia Autonomous Region","award":["2023YFSW0006"],"award-info":[{"award-number":["2023YFSW0006"]}]},{"name":"National Nature Science Foundation of China","award":["62071039"],"award-info":[{"award-number":["62071039"]}]},{"name":"Beijing Natural Science Foundation","award":["L223033"],"award-info":[{"award-number":["L223033"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681182","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"7094-7103","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ListenFormer: Responsive Listening Head Generation with Non-autoregressive Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2039-2051","authenticated-orcid":false,"given":"Miao","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3653-9951","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9511-6713","authenticated-orcid":false,"given":"Xinyuan","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong (Shenzhen) & National University of Singapore, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-2466.2005.tb02680.x"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"e_1_3_2_1_4_1","article-title":"A no reference image blur detection using cumulative probability blur detection (cpbd) metric","volume":"1","author":"Bohr P","year":"2013","unstructured":"P Bohr, Rupali Gargote, Rupali Vhorkate, RU Yawle, and VK Bairagi. 2013. A no reference image blur detection using cumulative probability blur detection (cpbd) metric. International Journal of Science and Modern Engineering, Vol. 1, 5 (2013).","journal-title":"International Journal of Science and Modern Engineering"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1891903.1891910"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192272"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612869"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.103028"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"e_1_3_2_1_10_1","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16344--16359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206272"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747157"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00518"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428081"},{"key":"e_1_3_2_1_19_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3258900"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551577"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551574"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"volume-title":"Organization of behavior in face-to-face interaction","author":"Kendon Adam","key":"e_1_3_2_1_24_1","unstructured":"Adam Kendon, Richard M Harris, and Mary R Key. 2011. Organization of behavior in face-to-face interaction. Walter de Gruyter."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"e_1_3_2_1_26_1","volume-title":"Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Lee JDMCK","year":"2018","unstructured":"JDMCK Lee and K Toutanova. 2018. Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, Vol. 3 (2018), 8."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the Asian Conference on Computer Vision.","author":"Lin Yan-Bo","year":"2020","unstructured":"Yan-Bo Lin and Yu-Chiang Frank Wang. 2020. Audiovisual transformer with instance attention for audio-visual event localization. In Proceedings of the Asian Conference on Computer Vision."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612123"},{"key":"e_1_3_2_1_31_1","volume-title":"OPT: One-shot Pose-Controllable Talking Head Generation. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5.","author":"Liu Jin","year":"2023","unstructured":"Jin Liu, Xi Wang, Xiaomeng Fu, Yesheng Chai, Cai Yu, Jiao Dai, and Jizhong Han. 2023. OPT: One-shot Pose-Controllable Talking Head Generation. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00513"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1177\/0271121407311241"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"e_1_3_2_1_36_1","volume-title":"Interactive generative adversarial networks for facial expression generation in dyadic interactions. arXiv preprint arXiv:1801.09092","author":"Nojavanasghari Behnaz","year":"2018","unstructured":"Behnaz Nojavanasghari, Yuchi Huang, and Saad Khan. 2018. Interactive generative adversarial networks for facial expression generation in dyadic interactions. arXiv preprint arXiv:1801.09092 (2018)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2000.0070453"},{"key":"e_1_3_2_1_38_1","volume-title":"Train short, test long: Attention with linear biases enables input length extrapolation. arXiv preprint arXiv:2108.12409","author":"Press Ofir","year":"2021","unstructured":"Ofir Press, Noah A Smith, and Mike Lewis. 2021. Train short, test long: Attention with linear biases enables input length extrapolation. arXiv preprint arXiv:2108.12409 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"volume-title":"Active listening","author":"Rost Michael","key":"e_1_3_2_1_40_1","unstructured":"Michael Rost and JJ Wilson. 2013. Active listening. Routledge."},{"key":"e_1_3_2_1_41_1","volume-title":"Emotional Listener Portrait: Realistic Listener Motion Simulation in Conversation. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE","author":"Song Luchuan","year":"2023","unstructured":"Luchuan Song, Guojun Yin, Zhenchao Jin, Xiaoyi Dong, and Chenliang Xu. 2023. Emotional Listener Portrait: Realistic Listener Motion Simulation in Conversation. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, 20782--20792."},{"key":"e_1_3_2_1_42_1","volume-title":"Multimodal sparse transformer network for audio-visual speech recognition","author":"Song Qiya","year":"2022","unstructured":"Qiya Song, Bin Sun, and Shutao Li. 2022. Multimodal sparse transformer network for audio-visual speech recognition. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_1_44_1","volume-title":"A length-extrapolatable transformer. arXiv preprint arXiv:2212.10554","author":"Sun Yutao","year":"2022","unstructured":"Yutao Sun, Li Dong, Barun Patra, Shuming Ma, Shaohan Huang, Alon Benhaim, Vishrav Chaudhary, Xia Song, and Furu Wei. 2022. A length-extrapolatable transformer. arXiv preprint arXiv:2212.10554 (2022)."},{"volume-title":"Origins of human communication","author":"Tomasello Michael","key":"e_1_3_2_1_45_1","unstructured":"Michael Tomasello. 2010. Origins of human communication. MIT press."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747278"},{"key":"e_1_3_2_1_47_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems Vol. 30 (2017)."},{"key":"e_1_3_2_1_48_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_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_2_1_50_1","volume-title":"Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang, Belinda Z Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)."},{"key":"e_1_3_2_1_51_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_52_1","volume-title":"Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3607541.3616820"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551580"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_8"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00610"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681182","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":58,"alternative-id":["10.1145\/3664647.3681182","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681182","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"}}]}}