{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:03:52Z","timestamp":1793131432238,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076227"],"award-info":[{"award-number":["62076227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Wuhan Applied Fundamental Frontier Project","award":["2020010601012166"],"award-info":[{"award-number":["2020010601012166"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548190","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T11:43:12Z","timestamp":1665402192000},"page":"24-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":94,"title":["MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild"],"prefix":"10.1145","author":[{"given":"Yuanyuan","family":"Liu","sequence":"first","affiliation":[{"name":"China University of Geosciences (Wuhan), Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Dai","sequence":"additional","affiliation":[{"name":"CUG, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanxu","family":"Feng","sequence":"additional","affiliation":[{"name":"CUG, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Wang","sequence":"additional","affiliation":[{"name":"CUG, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghao","family":"Yin","sequence":"additional","affiliation":[{"name":"CUG, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiabei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"e_1_3_2_2_4_1","volume-title":"Intelligent Teaching Evaluation System Integrating Facial Expression and Behavior Recognition in Teaching Video. In 2021 IEEE International Conference on Big Data and Smart Computing (BigComp). 52--59","author":"Chen Zheng","year":"2021","unstructured":"Zheng Chen , Meiyu Liang , Wanying Yu , Yongkang Huang , and Xiaoxiao Wang . 2021 . Intelligent Teaching Evaluation System Integrating Facial Expression and Behavior Recognition in Teaching Video. In 2021 IEEE International Conference on Big Data and Smart Computing (BigComp). 52--59 . https:\/\/doi.org\/10.1109\/BigComp51126.2021.00019 Zheng Chen, Meiyu Liang, Wanying Yu, Yongkang Huang, and Xiaoxiao Wang. 2021. Intelligent Teaching Evaluation System Integrating Facial Expression and Behavior Recognition in Teaching Video. In 2021 IEEE International Conference on Big Data and Smart Computing (BigComp). 52--59. https:\/\/doi.org\/10.1109\/BigComp51126.2021.00019"},{"key":"e_1_3_2_2_5_1","first-page":"2047","article-title":"Crowdsourcing quality control model protecting location privacy of workers","volume":"36","author":"Chu Xiang","year":"2016","unstructured":"Xiang Chu and Qiuyan Zhong . 2016 . Crowdsourcing quality control model protecting location privacy of workers . Systems Engineering - Theory & Practice 36 , 8 (2016), 2047 -- 2055 . https:\/\/doi.org\/10.12011\/1000--6788(2016)08--2047-09 Xiang Chu and Qiuyan Zhong. 2016. Crowdsourcing quality control model protecting location privacy of workers. Systems Engineering - Theory & Practice 36, 8 (2016), 2047--2055. https:\/\/doi.org\/10.12011\/1000--6788(2016)08--2047-09","journal-title":"Systems Engineering - Theory & Practice"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02310555"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143004"},{"key":"e_1_3_2_2_8_1","volume-title":"Multi-Task Learning and ArcFace. In 30th British Machine Vision Conference (BMVC).","author":"Dimitrios Kollias","year":"2019","unstructured":"Kollias Dimitrios and Zafeiriou Stefanos . 2019 . Expression, Affect, Action Unit Recognition: Aff-Wild2 , Multi-Task Learning and ArcFace. In 30th British Machine Vision Conference (BMVC). Kollias Dimitrios and Zafeiriou Stefanos. 2019. Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace. In 30th British Machine Vision Conference (BMVC)."},{"key":"e_1_3_2_2_9_1","volume-title":"9th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=YicbFdNTTy","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy , Lucas Beyer , Alexander Kolesnikov , Dirk Weissenborn , Xiaohua Zhai , Thomas Unterthiner , Mostafa Dehghani , Matthias Minderer , Georg Heigold , Sylvain Gelly , Jakob Uszkoreit , and Neil Houlsby . 2021 . An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale . In 9th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=YicbFdNTTy Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1322355111"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00078"},{"key":"e_1_3_2_2_12_1","volume-title":"Expression and the nature of emotion. Approaches to Emotion","author":"Ekman Paul","year":"1984","unstructured":"Paul Ekman . 1984. Expression and the nature of emotion. Approaches to Emotion ( 1984 ). Paul Ekman. 1984. Expression and the nature of emotion. Approaches to Emotion (1984)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1037\/0003-066X.48.4.384"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930434"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531923.2531924"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991218"},{"key":"e_1_3_2_2_17_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778","author":"He Kaiming","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016 . Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778 . https:\/\/doi.org\/10.1109\/CVPR.2016.90 Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778. https:\/\/doi.org\/10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.33"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1052"},{"key":"e_1_3_2_2_22_1","volume-title":"Context-Aware Emotion Recognition Networks. In IEEE\/CVF International Conference on Computer Vision (ICCV). 10142--10151","author":"Lee Jiyoung","year":"2019","unstructured":"Jiyoung Lee , Seungryong Kim , Sunok Kim , Jungin Park , and Kwanghoon Sohn . 2019 . Context-Aware Emotion Recognition Networks. In IEEE\/CVF International Conference on Computer Vision (ICCV). 10142--10151 . https:\/\/doi.org\/10.1109\/ICCV.2019.01024 Jiyoung Lee, Seungryong Kim, Sunok Kim, Jungin Park, and Kwanghoon Sohn. 2019. Context-Aware Emotion Recognition Networks. In IEEE\/CVF International Conference on Computer Vision (ICCV). 10142--10151. https:\/\/doi.org\/10.1109\/ICCV.2019.01024"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"e_1_3_2_2_24_1","volume-title":"Deep Facial Expression Recognition: A Survey","author":"Li Shan","year":"2020","unstructured":"Shan Li and Weihong Deng . 2020. Deep Facial Expression Recognition: A Survey . IEEE Transactions on Affective Computing 01 (mar 2020 ), 1--1. https:\/\/doi.org\/10.1109\/TAFFC.2020.2981446 Shan Li and Weihong Deng. 2020. Deep Facial Expression Recognition: A Survey. IEEE Transactions on Affective Computing 01 (mar 2020), 1--1. https:\/\/doi.org\/10.1109\/TAFFC.2020.2981446"},{"key":"e_1_3_2_2_25_1","volume-title":"Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2584--2593","author":"Li Shan","year":"2017","unstructured":"Shan Li , Weihong Deng , and JunPing Du . 2017 . Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2584--2593 . https:\/\/doi.org\/10.1109\/CVPR.2017.277 Shan Li, Weihong Deng, and JunPing Du. 2017. Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2584--2593. https:\/\/doi.org\/10.1109\/CVPR.2017.277"},{"key":"e_1_3_2_2_26_1","volume-title":"Deep Learning Face Attributes in the Wild. In IEEE International Conference on Computer Vision (ICCV). 3730--3738","author":"Liu Ziwei","year":"2015","unstructured":"Ziwei Liu , Ping Luo , Xiaogang Wang , and Xiaoou Tang . 2015 . Deep Learning Face Attributes in the Wild. In IEEE International Conference on Computer Vision (ICCV). 3730--3738 . https:\/\/doi.org\/10.1109\/ICCV.2015.425 Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. 2015. Deep Learning Face Attributes in the Wild. In IEEE International Conference on Computer Vision (ICCV). 3730--3738. https:\/\/doi.org\/10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_2_27_1","volume-title":"Mel Frequency Cepstral Coefficients for Music Modeling. In 1st International Symposium on Music Information Retrieval (ISMIR).","author":"Logan Beth","year":"2000","unstructured":"Beth Logan . 2000 . Mel Frequency Cepstral Coefficients for Music Modeling. In 1st International Symposium on Music Information Retrieval (ISMIR). Beth Logan. 2000. Mel Frequency Cepstral Coefficients for Music Modeling. In 1st International Symposium on Music Information Retrieval (ISMIR)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"e_1_3_2_2_29_1","volume-title":"Frame Attention Networks for Facial Expression Recognition in Videos. In IEEE International Conference on Image Processing (ICIP). 3866--3870","author":"Meng Debin","year":"2019","unstructured":"Debin Meng , Xiaojiang Peng , Kai Wang , and Yu Qiao . 2019 . Frame Attention Networks for Facial Expression Recognition in Videos. In IEEE International Conference on Image Processing (ICIP). 3866--3870 . https:\/\/doi.org\/10.1109\/ICIP.2019.8803603 Debin Meng, Xiaojiang Peng, Kai Wang, and Yu Qiao. 2019. Frame Attention Networks for Facial Expression Recognition in Videos. In IEEE International Conference on Image Processing (ICIP). 3866--3870. https:\/\/doi.org\/10.1109\/ICIP.2019.8803603"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"e_1_3_2_2_31_1","volume-title":"IEEE International Conference on Multimedia and Expo (ICME). 317--320","author":"Pantic M.","year":"2005","unstructured":"M. Pantic , M. Valstar , R. Rademaker , and L. Maat . 2005. Web-based database for facial expression analysis . In IEEE International Conference on Multimedia and Expo (ICME). 317--320 . https:\/\/doi.org\/10.1109\/ICME. 2005 .1521424 M. Pantic, M. Valstar, R. Rademaker, and L. Maat. 2005. Web-based database for facial expression analysis. In IEEE International Conference on Multimedia and Expo (ICME). 317--320. https:\/\/doi.org\/10.1109\/ICME.2005.1521424"},{"key":"e_1_3_2_2_32_1","first-page":"4","article-title":"A general psychoevolutionary theory of emotion","volume":"21","author":"Plutchik R.","year":"2000","unstructured":"R. Plutchik . 2000 . A general psychoevolutionary theory of emotion . Emotion Theory Research & Experience 21 , 4 -- 5 (2000), 529--553. R. Plutchik. 2000. A general psychoevolutionary theory of emotion. Emotion Theory Research & Experience 21, 4--5 (2000), 529--553.","journal-title":"Emotion Theory Research & Experience"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3483598"},{"key":"e_1_3_2_2_34_1","first-page":"20","article-title":"Maximum Likelihood Estimation of Observer Error-Rates Using the EM Algorithm","volume":"28","author":"Dawida A. P.","year":"1979","unstructured":"A. P. Dawida . M. Skene . 1979 . Maximum Likelihood Estimation of Observer Error-Rates Using the EM Algorithm . Journal of the Royal Statistical Society 28 , 1 (1979), 20 -- 28 . A. P. Dawida. M. Skene. 1979. Maximum Likelihood Estimation of Observer Error-Rates Using the EM Algorithm. Journal of the Royal Statistical Society 28, 1 (1979), 20--28.","journal-title":"Journal of the Royal Statistical Society"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9450.1988.tb00773.x"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS). Curran Associates Inc., 6000--6010","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017 . Attention is All You Need . In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS). Curran Associates Inc., 6000--6010 . Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS). Curran Associates Inc., 6000--6010."},{"key":"e_1_3_2_2_38_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Yu Hang","year":"2021","unstructured":"Hang Yu , Yufei Xu , Jing Zhang , Wei Zhao , Ziyu Guan , and Dacheng Tao . 2021 . AP-10K: A Benchmark for Animal Pose Estimation in the Wild . In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). Hang Yu, Yufei Xu, Jing Zhang, Wei Zhao, Ziyu Guan, and Dacheng Tao. 2021. AP-10K: A Benchmark for Animal Pose Estimation in the Wild. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806328"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548190","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:00:20Z","timestamp":1750172420000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":40,"alternative-id":["10.1145\/3503161.3548190","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548190","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}