{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:54:08Z","timestamp":1780635248359,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":54,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680921","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"2194-2203","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8909-9212","authenticated-orcid":false,"given":"Jianzhi","family":"Lu","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-3043","authenticated-orcid":false,"given":"Ruian","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7283-2314","authenticated-orcid":false,"given":"Shili","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7677-4772","authenticated-orcid":false,"given":"Weimin","family":"Tan","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0256-9682","authenticated-orcid":false,"given":"Bo","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","article-title":"Self-Supervised Approach for Facial Movement Based Optical Flow","author":"Alkaddour Muhannad","year":"2021","unstructured":"Muhannad Alkaddour, Usman Tariq, and Abhinav Dhall. 2021. Self-Supervised Approach for Facial Movement Based Optical Flow. IEEE Transactions on Affective Computing, IEEE Transactions on Affective Computing (May 2021).","journal-title":"IEEE Transactions on Affective Computing, IEEE Transactions on Affective Computing"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00043"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"M.J. Black and P. Anandan. 2002. A framework for the robust estimation of optical flow. In 1993 (4th) International Conference on Computer Vision. https: \/\/doi.org\/10.1109\/iccv.1993.378214","DOI":"10.1109\/iccv.1993.378214"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0006"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings, Part IV 8. Springer, 25--36","author":"Brox Thomas","year":"2004","unstructured":"Thomas Brox, Andr\u00e9s Bruhn, Nils Papenberg, and Joachim Weickert. 2004. High accuracy optical flow estimation based on a theory for warping. In Computer Vision-ECCV 2004: 8th European Conference on Computer Vision, Prague, Czech Republic, May 11--14, 2004. Proceedings, Part IV 8. Springer, 25--36."},{"key":"e_1_3_2_1_6_1","volume-title":"International Journal of Computer Vision, International Journal of Computer Vision (Feb","author":"Bruhn Andr\u00e9s","year":"2005","unstructured":"Andr\u00e9s Bruhn, Joachim Weickert, and Christoph Schn\u00f6rr. 2005. Lucas\/Kanade meets Horn\/Schunck: combining local and global optic flow methods. International Journal of Computer Vision, International Journal of Computer Vision (Feb 2005)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_5"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01172"},{"key":"e_1_3_2_1_10_1","volume-title":"EMOCA: Emotion Driven Monocular Face Capture and Animation. In Conference on Computer Vision and Pattern Recognition (CVPR). 20311--20322","author":"Danecek Radek","year":"2022","unstructured":"Radek Danecek, Michael J. Black, and Timo Bolkart. 2022. EMOCA: Emotion Driven Monocular Face Capture and Animation. In Conference on Computer Vision and Pattern Recognition (CVPR). 20311--20322."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3087709"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00135"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6248074"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_17"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_2_1_18_1","volume-title":"Hongwei Qin, Jifeng Dai, and Hongsheng Li.","author":"Huang Zhaoyang","year":"2022","unstructured":"Zhaoyang Huang, Xiaoyu Shi, Chao Zhang, Qiang Wang, Ka Chun Cheung, Hongwei Qin, Jifeng Dai, and Hongsheng Li. 2022. Flow Former: A Transformer Architecture for Optical Flow. ECCV (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.179"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01316"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3004359"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Daniel Kondermann Rahul Nair Katrin Honauer Karsten Krispin Jonas Andrulis Alexander Brock Burkhard Gussefeld Mohsen Rahimimoghaddam Sabine Hofmann Claus Brenner and Bernd Jahne. 2016. The HCI Benchmark Suite: Stereo and Flow Ground Truth with Uncertainties for Urban Autonomous Driving. In 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). https:\/\/doi.org\/10.1109\/cvprw.2016.10","DOI":"10.1109\/cvprw.2016.10"},{"key":"e_1_3_2_1_24_1","volume-title":"Deep- FaceFlow: In-the-wild Dense 3D Facial Motion Estimation","author":"Koujan Mohammad Rami","year":"2020","unstructured":"Mohammad Rami Koujan, Anastasios Roussos, and Stefanos Zafeiriou. 2020. Deep- FaceFlow: In-the-wild Dense 3D Facial Motion Estimation. Cornell University - arXiv,Cornell University - arXiv (May 2020)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/fg47880.2020.00048"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/150"},{"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","unstructured":"Tianye Li Timo Bolkart Michael. J. Black Hao Li and Javier Romero. 2020. Photometric FLAME Fitting. https:\/\/github.com\/HavenFeng\/photometric_ optimization\/."},{"key":"e_1_3_2_1_29_1","unstructured":"Tianye Li Timo Bolkart Michael. J. Black Hao Li and Javier Romero. 2021. BFM to FLAME. https:\/\/github.com\/TimoBolkart\/BFM_to_FLAME\/."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2010.5543262"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02027"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.438"},{"key":"e_1_3_2_1_33_1","volume-title":"Optical Flow and Stereo. Conference on Computer Vision and Pattern Recognition (Mar","author":"Mehl Lukas","year":"2023","unstructured":"Lukas Mehl, Jenny Schmalfuss, Azin Jahedi, Yaroslava Nalivayko, and Andres Bruhn. 2023. Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo. Conference on Computer Vision and Pattern Recognition (Mar 2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298925"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"e_1_3_2_1_36_1","volume-title":"Automatic differentiation in PyTorch. (Oct","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, EdwardZ. Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in PyTorch. (Oct 2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/avss.2009.58"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01279-w"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.272"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00996"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"e_1_3_2_1_43_1","first-page":"11313","article-title":"Skflow: Learning optical flow with super kernels","volume":"35","author":"Sun Shangkun","year":"2022","unstructured":"Shangkun Sun, Yuanqi Chen, Yu Zhu, Guodong Guo, and Ge Li. 2022. Skflow: Learning optical flow with super kernels. Advances in Neural Information Processing Systems 35 (2022), 11313--11326.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision--ECCV 2020: 16th European Conference","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part II 16. Springer, 402--419."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. https:\/\/doi.org\/10","author":"Viola P.","year":"2001","unstructured":"P. Viola and M. Jones. 2005. Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. https:\/\/doi.org\/10.1109\/ cvpr.2001.990517"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_2_1_47_1","volume-title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","author":"Wen Zhengyao","year":"2021","unstructured":"Zhengyao Wen, Wenzhong Lin, Tao Wang, and Ge Xu. 2021. Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition. Cornell University - arXiv,Cornell University - arXiv (Sep 2021)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00402"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0086041"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00401"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00366"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28603"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_15"}],"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\/3664647.3680921","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":54,"alternative-id":["10.1145\/3664647.3680921","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680921","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"}}]}}