{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:10:10Z","timestamp":1742976610833,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030873578"},{"type":"electronic","value":"9783030873585"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87358-5_37","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T23:54:11Z","timestamp":1632959651000},"page":"461-472","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Facial Action Unit Detection Based on Transformer and Attention Mechanism"],"prefix":"10.1007","author":[{"given":"Wenyu","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuze","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoyun","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"37_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"37_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Corneanu, C., Madadi, M., Escalera, S.: Deep structure inference network for facial action unit recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 298\u2013313 (2018)","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Ekman, R.: What the Face Reveals: Basic and Applied Studies of Spontaneous Expression using the Facial Action Coding System (FACS). Oxford University Press, USA (1997)","DOI":"10.1093\/oso\/9780195104462.001.0001"},{"key":"37_CR6","unstructured":"Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: a library for large linear classification. J. Mach. Learn. Res. 9, 1871\u20131874 (2008)"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Lakshminarayana, N., Setlur, S., Govindaraju, V.: Learning guided attention masks for facial action unit recognition. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 465\u2013472. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00128"},{"issue":"11","key":"37_CR9","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1109\/TPAMI.2018.2791608","volume":"40","author":"W Li","year":"2018","unstructured":"Li, W., Abtahi, F., Zhu, Z., Yin, L.: Eac-net: deep nets with enhancing and cropping for facial action unit detection. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2583\u20132596 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"37_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/978-3-030-37734-2_40","volume-title":"MultiMedia Modeling","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Dong, J., Zhang, C., Wang, L., Dang, J.: Relation modeling with graph convolutional networks for facial action unit detection. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 489\u2013501. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37734-2_40"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Niu, X., Han, H., Yang, S., Huang, Y., Shan, S.: Local relationship learning with person-specific shape regularization for facial action unit detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11917\u201311926 (2019)","DOI":"10.1109\/CVPR.2019.01219"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Sankaran, N., Mohan, D.D., Setlur, S., Govindaraju, V., Fedorishin, D.: Representation learning through cross-modality supervision. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756519"},{"issue":"6","key":"37_CR14","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/j.imavis.2008.08.005","volume":"27","author":"C Shan","year":"2009","unstructured":"Shan, C., Gong, S., McOwan, P.W.: Facial expression recognition based on local binary patterns: a comprehensive study. Image Vis. Comput. 27(6), 803\u2013816 (2009)","journal-title":"Image Vis. Comput."},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Shao, Z., Liu, Z., Cai, J., Ma, L.: Deep adaptive attention for joint facial action unit detection and face alignment. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 705\u2013720 (2018)","DOI":"10.1007\/978-3-030-01261-8_43"},{"issue":"2","key":"37_CR16","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s11263-020-01378-z","volume":"129","author":"Z Shao","year":"2021","unstructured":"Shao, Z., Liu, Z., Cai, J., Ma, L.: Jaa-net: joint facial action unit detection and face alignment via adaptive attention. Int. J. Comput. Vis. 129(2), 321\u2013340 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Shao, Z., Liu, Z., Cai, J., Wu, Y., Ma, L.: Facial action unit detection using attention and relation learning. IEEE Transactions on Affective Computing (2019)","DOI":"10.1109\/TAFFC.2019.2948635"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Shi, S., An, G., Ruan, Q.: Multi-scale region with local relationship learning for facial action unit detection. In: 2020 15th IEEE International Conference on Signal Processing (ICSP), vol. 1, pp. 252\u2013256. IEEE (2020)","DOI":"10.1109\/ICSP48669.2020.9320954"},{"key":"37_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Valstar, M.F., et al.: Fera 2015-second facial expression recognition and analysis challenge. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 6, pp. 1\u20138. IEEE (2015)","DOI":"10.1109\/FG.2015.7284874"},{"key":"37_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. arXiv preprint arXiv:2011.14503 (2020)","DOI":"10.1109\/CVPR46437.2021.00863"},{"issue":"3","key":"37_CR23","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TBDATA.2015.2497270","volume":"1","author":"F Wu","year":"2015","unstructured":"Wu, F., et al.: Weakly semi-supervised deep learning for multi-label image annotation. IEEE Trans. Big Data 1(3), 109\u2013122 (2015)","journal-title":"IEEE Trans. Big Data"},{"issue":"10","key":"37_CR24","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1016\/j.imavis.2014.06.002","volume":"32","author":"X Zhang","year":"2014","unstructured":"Zhang, X., et al.: Bp4d-spontaneous: a high-resolution spontaneous 3D dynamic facial expression database. Image Vis. Comput. 32(10), 692\u2013706 (2014)","journal-title":"Image Vis. Comput."},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.S., De la Torre, F., Cohn, J.F., Zhang, H.: Joint patch and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2207\u20132216 (2015)","DOI":"10.1109\/CVPR.2015.7298833"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.S., Zhang, H.: Deep region and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3391\u20133399 (2016)","DOI":"10.1109\/CVPR.2016.369"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, F., Li, H., Ouyang, W., Yu, N., Wang, X.: Learning spatial regularization with image-level supervisions for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5513\u20135522 (2017)","DOI":"10.1109\/CVPR.2017.219"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87358-5_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T01:28:32Z","timestamp":1725845312000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87358-5_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030873578","9783030873585"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87358-5_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2021.csig.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"421","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"198","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference was postponed due to the COVID19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}