{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T03:59:12Z","timestamp":1777003152543,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T00:00:00Z","timestamp":1716508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of Jiangsu Province","award":["No.BK20171249"],"award-info":[{"award-number":["No.BK20171249"]}]},{"name":"Natural Science Foundation of China","award":["No.60871086"],"award-info":[{"award-number":["No.60871086"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,24]]},"DOI":"10.1145\/3670105.3670210","type":"proceedings-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T18:29:36Z","timestamp":1722277776000},"page":"600-605","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Facial Action Unit Recognition Based on Self-Attention Spatiotemporal Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4757-0544","authenticated-orcid":false,"given":"Chaolei","family":"Liang","sequence":"first","affiliation":[{"name":"SooChow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2704-0021","authenticated-orcid":false,"given":"Wei","family":"Zou","sequence":"additional","affiliation":[{"name":"SooChow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9821-5356","authenticated-orcid":false,"given":"Danfeng","family":"Hu","sequence":"additional","affiliation":[{"name":"SooChow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4843-2040","authenticated-orcid":false,"given":"Jiajun","family":"Wang","sequence":"additional","affiliation":[{"name":"SooChow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Fernando De\u00a0la Torre, and Jeffrey\u00a0F Cohn","author":"Chu Wen-Sheng","year":"2016","unstructured":"Wen-Sheng Chu, Fernando De\u00a0la Torre, and Jeffrey\u00a0F Cohn. 2016. Modeling spatial and temporal cues for multi-label facial action unit detection. arXiv preprint arXiv:1608.00911 (2016)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1322355111"},{"key":"e_1_3_2_1_3_1","volume-title":"Facial action coding system. Environmental Psychology & Nonverbal Behavior","author":"Ekman Paul","year":"1978","unstructured":"Paul Ekman and Wallace\u00a0V Friesen. 1978. Facial action coding system. Environmental Psychology & Nonverbal Behavior (1978)."},{"key":"e_1_3_2_1_4_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735\u20131780."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7680\u20137689","author":"Jacob Geethu\u00a0Miriam","year":"2021","unstructured":"Geethu\u00a0Miriam Jacob and Bjorn Stenger. 2021. Facial action unit detection with transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7680\u20137689."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.716"},{"key":"e_1_3_2_1_8_1","volume-title":"Eac-net: Deep nets with enhancing and cropping for facial action unit detection","author":"Li Wei","year":"2018","unstructured":"Wei Li, Farnaz Abtahi, Zhigang Zhu, and Lijun Yin. 2018. Eac-net: Deep nets with enhancing and cropping for facial action unit detection. IEEE transactions on pattern analysis and machine intelligence 40, 11 (2018), 2583\u20132596."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"e_1_3_2_1_10_1","volume-title":"Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172","author":"Lugaresi Camillo","year":"2019","unstructured":"Camillo Lugaresi, Jiuqiang Tang, Hadon Nash, Chris McClanahan, Esha Uboweja, Michael Hays, Fan Zhang, Chuo-Ling Chang, Ming\u00a0Guang Yong, Juhyun Lee, 2019. Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)."},{"key":"e_1_3_2_1_11_1","volume-title":"Learning multi-dimensional edge feature-based au relation graph for facial action unit recognition. arXiv preprint arXiv:2205.01782","author":"Luo Cheng","year":"2022","unstructured":"Cheng Luo, Siyang Song, Weicheng Xie, Linlin Shen, and Hatice Gunes. 2022. Learning multi-dimensional edge feature-based au relation graph for facial action unit recognition. arXiv preprint arXiv:2205.01782 (2022)."},{"key":"e_1_3_2_1_12_1","volume-title":"Au r-cnn: Encoding expert prior knowledge into r-cnn for action unit detection. neurocomputing 355","author":"Ma Chen","year":"2019","unstructured":"Chen Ma, Li Chen, and Junhai Yong. 2019. Au r-cnn: Encoding expert prior knowledge into r-cnn for action unit detection. neurocomputing 355 (2019), 35\u201347."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"e_1_3_2_1_14_1","volume-title":"D-pattnet: Dynamic patch-attentive deep network for action unit detection. Frontiers in computer science 1","author":"Onal\u00a0Ertugrul Itir","year":"2019","unstructured":"Itir Onal\u00a0Ertugrul, Le Yang, L\u00e1szl\u00f3\u00a0A Jeni, and Jeffrey\u00a0F Cohn. 2019. D-pattnet: Dynamic patch-attentive deep network for action unit detection. Frontiers in computer science 1 (2019), 11."},{"key":"e_1_3_2_1_15_1","volume-title":"Joint action unit localisation and intensity estimation through heatmap regression. arXiv preprint arXiv:1805.03487","author":"S\u00e1nchez-Lozano Enrique","year":"2018","unstructured":"Enrique S\u00e1nchez-Lozano, Georgios Tzimiropoulos, and Michel Valstar. 2018. Joint action unit localisation and intensity estimation through heatmap regression. arXiv preprint arXiv:1805.03487 (2018)."},{"key":"e_1_3_2_1_16_1","volume-title":"The graph neural network model","author":"Scarselli Franco","year":"2008","unstructured":"Franco Scarselli, Marco Gori, Ah\u00a0Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks 20, 1 (2008), 61\u201380."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"e_1_3_2_1_18_1","volume-title":"Facial action unit detection using attention and relation learning","author":"Shao Zhiwen","year":"2019","unstructured":"Zhiwen Shao, Zhilei Liu, Jianfei Cai, Yunsheng Wu, and Lizhuang Ma. 2019. Facial action unit detection using attention and relation learning. IEEE transactions on affective computing 13, 3 (2019), 1274\u20131289."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277794"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16748"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.11.010"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914231"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475674"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88004-0_7"}],"event":{"name":"CNIOT 2024: 2024 5th International Conference on Computing, Networks and Internet of Things","location":"Tokyo Japan","acronym":"CNIOT 2024"},"container-title":["Proceedings of the 2024 5th International Conference on Computing, Networks and Internet of Things"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670105.3670210","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3670105.3670210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:51:12Z","timestamp":1755877872000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670105.3670210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,24]]},"references-count":27,"alternative-id":["10.1145\/3670105.3670210","10.1145\/3670105"],"URL":"https:\/\/doi.org\/10.1145\/3670105.3670210","relation":{},"subject":[],"published":{"date-parts":[[2024,5,24]]},"assertion":[{"value":"2024-07-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}