{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:25:23Z","timestamp":1780637123116,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":30,"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:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"the National Natural Science Foundation of China (NSFC)","award":["No.61831022, No.62276259, No.62201572, No.U21B2010, No.62271083"],"award-info":[{"award-number":["No.61831022, No.62276259, No.62201572, No.U21B2010, No.62271083"]}]},{"name":"Open Research Projects of Zhejiang Lab","award":["NO. 2021KH0AB06"],"award-info":[{"award-number":["NO. 2021KH0AB06"]}]},{"name":"Beijing Municipal Science&Technology Commission,Administrative Commission of Zhongguancun Science Park","award":["No.Z211100004821013"],"award-info":[{"award-number":["No.Z211100004821013"]}]},{"name":"CCF- Baidu Open Fund","award":["No.OF2022025"],"award-info":[{"award-number":["No.OF2022025"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612868","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"9576-9580","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Integrating VideoMAE based model and Optical Flow for Micro- and Macro-expression Spotting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3563-9720","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4224-3644","authenticated-orcid":false,"given":"Kang","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking university,Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9019-1725","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3698-1057","authenticated-orcid":false,"given":"Gong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3485-3869","authenticated-orcid":false,"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3948-9054","authenticated-orcid":false,"given":"Mingyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3654-4774","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"deception, and facial expression[J]. Annals of the new York Academy of sciences","author":"Ekman P.","year":"2003","unstructured":"Ekman P. Darwin, deception, and facial expression[J]. Annals of the new York Academy of sciences, 2003, 1000(1): 205--221."},{"key":"e_1_3_2_1_2_1","volume-title":"Towards reading hidden emotions: A comparative study of spontaneous micro-expression spotting and recognition methods[J]","author":"Li X","year":"2017","unstructured":"Li X, Hong X, Moilanen A, et al. Towards reading hidden emotions: A comparative study of spontaneous micro-expression spotting and recognition methods[J]. IEEE transactions on affective computing, 2017, 9(4): 563--577."},{"key":"e_1_3_2_1_3_1","volume-title":"The design and development of a lie detection system using facial micro-expression[C]\/\/2012 2nd international conference on advances in computational tools for engineering applications (ACTEA)","author":"Owayjan M","year":"2012","unstructured":"Owayjan M, Kashour A, Al Haddad N, et al. The design and development of a lie detection system using facial micro-expression[C]\/\/2012 2nd international conference on advances in computational tools for engineering applications (ACTEA). IEEE, 2012: 33--38."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2316163"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-013-0159-8"},{"key":"e_1_3_2_1_6_1","volume-title":"Research on micro-expression spotting method based on optical flow features[C]\/\/Proceedings of the 29th ACM International Conference on Multimedia. 2021: 4803--4807","author":"Yuhong H.","unstructured":"Yuhong H. Research on micro-expression spotting method based on optical flow features[C]\/\/Proceedings of the 29th ACM International Conference on Multimedia. 2021: 4803--4807."},{"key":"e_1_3_2_1_7_1","volume-title":"Facial expression spotting based on optical flow features[C]\/\/Proceedings of the 30th ACM International Conference on Multimedia. 2022: 7205--7209","author":"Yu J","unstructured":"Yu J, Cai Z, Liu Z, et al. Facial expression spotting based on optical flow features[C]\/\/Proceedings of the 30th ACM International Conference on Multimedia. 2022: 7205--7209."},{"key":"e_1_3_2_1_8_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training[J]. Advances in neural information processing systems","author":"Tong Z","year":"2022","unstructured":"Tong Z, Song Y, Wang J, et al. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training[J]. Advances in neural information processing systems, 2022, 35: 10078--10093."},{"key":"e_1_3_2_1_9_1","volume-title":"Micro Expression Training Tool (METT)","author":"Ekman","year":"2002","unstructured":"P. Ekman, Micro Expression Training Tool (METT). San Francisco, CA, USA: Univ. California, 2002."},{"key":"e_1_3_2_1_10_1","volume-title":"?Facial action coding system (FACS): a technique for the measurement of facial actions,\" Rivista Di Psichiatria","author":"Ekman W. V.","unstructured":"P. Ekman and W. V. Friesen, ?Facial action coding system (FACS): a technique for the measurement of facial actions,\" Rivista Di Psichiatria, vol. 47, no. 2, pp. 126--38, 1978."},{"key":"e_1_3_2_1_11_1","first-page":"1","volume-title":"IEEE Conf. Appl. Comput Vis.","author":"Shreve S.","year":"2009","unstructured":"M. Shreve, S. Godavarthy, V. Manohar, D. Goldgof, and S. Sarkar, ?Towards macro- and micro-expression spotting in video using strain patterns,'' in Proc. IEEE Conf. Appl. Comput Vis., Dec. 2009, pp. 1--6."},{"key":"e_1_3_2_1_12_1","first-page":"51","volume-title":"IEEE Conf. Auto Face Gesture Recognit.","author":"Shreve S.","year":"2011","unstructured":"M. Shreve, S. Godavarthy, D. Goldgof, and S. Sarkar, ??Macro- and micro expression spotting in long videos using spatio-temporal strain,'' in Proc. IEEE Conf. Auto Face Gesture Recognit., Mar. 2011, pp. 51--56."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0006"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756626"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3064258"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00052"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1042.2022.02143"},{"key":"e_1_3_2_1_18_1","volume-title":"Adrian K. Davison, and Ryan Cunningham.","author":"Chuin Hong Yap","year":"2021","unstructured":"Chuin Hong Yap, Moi Hoon Yap, Adrian K. Davison, and Ryan Cunningham. 2021.Efficient Lightweight 3D-CNN using Frame Skipping and Contrast Enhancement for Facial Macro- and Micro-expression Spotting. CoRR abs\/2105.06340 (2021).arXiv:2105.06340 https:\/\/arxiv.org\/abs\/2105.06340"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yap C H Yap M H Davison A et al. 3d-cnn for facial micro-and macro-expression spotting on long video sequences using temporal oriented reference frame[C]\/\/Proceedings of the 30th ACM International Conference on Multimedia. 2022: 7016--7020.","DOI":"10.1145\/3503161.3551570"},{"key":"e_1_3_2_1_20_1","unstructured":"Zhan Tong Yibing Song Jue Wang and Limin Wang. 2022. VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_21_1","volume-title":"Dlib-ml: A machine learning toolkit. The Journal of Machine Learning Research 10","author":"Davis E","year":"2009","unstructured":"Davis E King. 2009. Dlib-ml: A machine learning toolkit. The Journal of Machine Learning Research 10 (2009), 1755--1758."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16000--16009","author":"Kaiming He","year":"2022","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16000--16009."},{"key":"e_1_3_2_1_23_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_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"e_1_3_2_1_25_1","volume-title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition[J]. arXiv preprint arXiv:2307.02227","author":"Sun L","year":"2023","unstructured":"Sun L, Lian Z, Liu B, et al. MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition[J]. arXiv preprint arXiv:2307.02227, 2023."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174895"},{"key":"e_1_3_2_1_27_1","volume-title":"SAMM: A spontaneous micro-facial movement dataset","author":"Davison A. K.","year":"2016","unstructured":"Davison, A. K., Lansley, C., Costen, N., Tan, K., & Yap, M. H. (2016). SAMM: A spontaneous micro-facial movement dataset. IEEE Transactions on Affective Computing, 9(1), 116--129."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00037"},{"key":"e_1_3_2_1_29_1","volume-title":"Facial expression spotting based on optical flow features[C]\/\/Proceedings of the 30th ACM International Conference on Multimedia. 2022: 7205--7209","author":"Yu J","unstructured":"Yu J, Cai Z, Liu Z, et al. Facial expression spotting based on optical flow features[C]\/\/Proceedings of the 30th ACM International Conference on Multimedia. 2022: 7205--7209."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Wu W. Peng H. & Yu S. YuNet: A Tiny Millisecond-level Face Detector. Mach. Intell. Res. (2023). https:\/\/doi.org\/10.1007\/s11633-023-1423-y","DOI":"10.1007\/s11633-023-1423-y"}],"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\/3581783.3612868","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:26Z","timestamp":1755820886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612868"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":30,"alternative-id":["10.1145\/3581783.3612868","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612868","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"}}]}}