{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:08Z","timestamp":1759331828621,"version":"3.28.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s10489-023-05154-7","type":"journal-article","created":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T06:01:41Z","timestamp":1704520901000},"page":"1405-1425","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Learning facial expression-aware global-to-local representation for robust action unit detection"],"prefix":"10.1007","volume":"54","author":[{"given":"Rudong","family":"An","sequence":"first","affiliation":[]},{"given":"Aobo","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Zhigang","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,6]]},"reference":[{"key":"5154_CR1","doi-asserted-by":"crossref","unstructured":"Chen J, Wang C, Wang K et\u00a0al (2022) Lightweight network architecture using difference saliency maps for facial action unit detection. App Intell 1\u201322","DOI":"10.1007\/s10489-021-02755-y"},{"key":"5154_CR2","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.patcog.2021.108355","volume":"122","author":"Y Chen","year":"2022","unstructured":"Chen Y, Song G, Shao Z et al (2022) Geoconv: geodesic guided convolution for facial action unit recognition. Pattern Recogn 122:108\u2013355","journal-title":"Pattern Recogn"},{"key":"5154_CR3","doi-asserted-by":"crossref","unstructured":"Chen ZM, Wei XS, Wang P et\u00a0al (2019) Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5177\u20135186","DOI":"10.1109\/CVPR.2019.00532"},{"key":"5154_CR4","doi-asserted-by":"crossref","unstructured":"Choi Y, Uh Y, Yoo J et\u00a0al (2020) Stargan v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8188\u20138197","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"5154_CR5","unstructured":"Cui Z, Song T, Wang Y et\u00a0al (2020) Knowledge augmented deep neural networks for joint facial expression and action unit recognition. Adv Neural Inf Process Syst 33"},{"key":"5154_CR6","doi-asserted-by":"crossref","unstructured":"Ekman P, Friesen W (1978) Facial action coding system: a technique for the measurement of facial movement. Consulting Psychologists Press Palo Alto 12","DOI":"10.1037\/t27734-000"},{"key":"5154_CR7","unstructured":"Ertugrul I\u00d6, Jeni LA, Cohn JF (2019) Pattnet: patch-attentive deep network for action unit detection. In: BMVC, p 114"},{"key":"5154_CR8","doi-asserted-by":"crossref","unstructured":"Geng Z, Cao C, Tulyakov S (2019) 3d guided fine-grained face manipulation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9821\u20139830","DOI":"10.1109\/CVPR.2019.01005"},{"key":"5154_CR9","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et\u00a0al (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"5154_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5154_CR11","doi-asserted-by":"crossref","unstructured":"Hu X, Zhi R, Zhou C (2023) Drop-relationship learning for semi-supervised facial action unit recognition. Neurocomputing p 126361","DOI":"10.1016\/j.neucom.2023.126361"},{"key":"5154_CR12","doi-asserted-by":"crossref","unstructured":"Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision, pp 1501\u20131510","DOI":"10.1109\/ICCV.2017.167"},{"key":"5154_CR13","unstructured":"Jacob GM, Stenger B (2021) Facial action unit detection with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7680\u20137689"},{"key":"5154_CR14","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25"},{"key":"5154_CR15","doi-asserted-by":"crossref","unstructured":"Li G, Zhu X, Zeng Y et\u00a0al (2019) Semantic relationships guided representation learning for facial action unit recognition. In: Proceedings of the AAAI conference on artificial intelligence, pp 8594\u20138601","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"5154_CR16","doi-asserted-by":"crossref","unstructured":"Li L, Wang S, Zhang Z et\u00a0al (2021) Write-a-speaker: text-based emotional and rhythmic talking-head generation. In: Proceedings of the AAAI conference on artificial intelligence, pp 1911\u20131920","DOI":"10.1609\/aaai.v35i3.16286"},{"issue":"11","key":"5154_CR17","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 et al (2018) Eac-net: deep nets with enhancing and cropping for facial action unit detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 40(11):2583\u20132596","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5154_CR18","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.neucom.2015.02.011","volume":"159","author":"M Liu","year":"2015","unstructured":"Liu M, Li S, Shan S et al (2015) Au-inspired deep networks for facial expression feature learning. Neurocomputing 159:126\u2013136","journal-title":"Neurocomputing"},{"key":"5154_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Wang H (2023) Talking face generation via facial anatomy. ACM Trans Multimedia Comput Commun Appl 19(3)","DOI":"10.1145\/3571746"},{"key":"5154_CR20","doi-asserted-by":"crossref","unstructured":"Luo C, Song S, Xie W et\u00a0al (2022) Learning multi-dimensional edge feature-based au relation graph for facial action unit recognition. In: Raedt LD (ed) Proceedings of international joint conference on artificial intelligence, pp 1239\u20131246","DOI":"10.24963\/ijcai.2022\/173"},{"key":"5154_CR21","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.neucom.2019.03.082","volume":"355","author":"C Ma","year":"2019","unstructured":"Ma C, Chen L, Yong J (2019) Au r-cnn: encoding expert prior knowledge into r-cnn for action unit detection. Neurocomputing 355:35\u201347","journal-title":"Neurocomputing"},{"issue":"2","key":"5154_CR22","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","volume":"4","author":"SM Mavadati","year":"2013","unstructured":"Mavadati SM, Mahoor MH, Bartlett K et al (2013) Disfa: a spontaneous facial action intensity database. IEEE Trans Affect Comput 4(2):151\u2013160","journal-title":"IEEE Trans Affect Comput"},{"issue":"1","key":"5154_CR23","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini A, Hasani B, Mahoor MH (2017) Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans Affect Comput 10(1):18\u201331","journal-title":"IEEE Trans Affect Comput"},{"key":"5154_CR24","doi-asserted-by":"crossref","unstructured":"Niu X, Han H, Yang S et\u00a0al (2019) Local relationship learning with person-specific shape regularization for facial action unit detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 11,917\u201311,926","DOI":"10.1109\/CVPR.2019.01219"},{"key":"5154_CR25","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3389\/fcomp.2019.00011","volume":"1","author":"I Onal Ertugrul","year":"2019","unstructured":"Onal Ertugrul I, Yang L, Jeni LA et al (2019) D-pattnet: dynamic patch-attentive deep network for action unit detection. Frontiers in Computer Science 1:11","journal-title":"Frontiers in Computer Science"},{"key":"5154_CR26","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1109\/TSMCB.2004.825931","volume":"34","author":"M Pantic","year":"2004","unstructured":"Pantic M, Rothkrantz L (2004) Facial action recognition for facial expression analysis from static face images. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on 34:1449\u20131461","journal-title":"Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on"},{"key":"5154_CR27","doi-asserted-by":"crossref","unstructured":"Paysan P, Knothe R, Amberg B et\u00a0al (2009) A 3d face model for pose and illumination invariant face recognition. In: IEEE international conference on advanced video and signal based surveillance, pp 296\u2013301","DOI":"10.1109\/AVSS.2009.58"},{"issue":"9","key":"5154_CR28","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/0006-3223(92)90120-O","volume":"31","author":"DR Rubinow","year":"1992","unstructured":"Rubinow DR, Post RM (1992) Impaired recognition of affect in facial expression in depressed patients. Biological psychiatry 31(9):947\u2013953","journal-title":"Biological psychiatry"},{"key":"5154_CR29","doi-asserted-by":"crossref","unstructured":"Shang Z, Du C, Li B et\u00a0al (2023) Mma-net: multi-view mixed attention mechanism for facial action unit detection. Pattern Recognition Letters","DOI":"10.1016\/j.patrec.2023.06.004"},{"key":"5154_CR30","doi-asserted-by":"crossref","unstructured":"Shao Z, Liu Z, Cai J et\u00a0al (2018) 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","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"5154_CR31","unstructured":"Shao Z, Liu Z, Cai J et\u00a0al (2019) Facial action unit detection using attention and relation learning. IEEE Transactions on Affective Computing"},{"issue":"2","key":"5154_CR32","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 et al (2021) Jaa-net: joint facial action unit detection and face alignment via adaptive attention. International Journal of Computer Vision 129(2):321\u2013340","journal-title":"International Journal of Computer Vision"},{"key":"5154_CR33","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.patrec.2022.11.010","volume":"164","author":"W Song","year":"2022","unstructured":"Song W, Shi S, Dong Y et al (2022) Heterogeneous spatio-temporal relation learning network for facial action unit detection. Pattern Recognition Letters 164:268\u2013275","journal-title":"Pattern Recognition Letters"},{"key":"5154_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V et\u00a0al (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"5154_CR35","unstructured":"Ulyanov D, Vedaldi A, Lempitsky V (2016) Instance normalization: The missing ingredient for fast stylization. arXiv:1607.08022"},{"key":"5154_CR36","doi-asserted-by":"crossref","unstructured":"Vemulapalli R, Agarwala A (2019) A compact embedding for facial expression similarity. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5683\u20135692","DOI":"10.1109\/CVPR.2019.00583"},{"issue":"12","key":"5154_CR37","doi-asserted-by":"publisher","first-page":"3218","DOI":"10.1109\/TMM.2019.2916063","volume":"21","author":"S Wang","year":"2019","unstructured":"Wang S, Peng G (2019) Weakly supervised dual learning for facial action unit recognition. IEEE Transactions on Multimedia 21(12):3218\u20133230","journal-title":"IEEE Transactions on Multimedia"},{"key":"5154_CR38","unstructured":"Wang S, Chang Y, Wang C (2021) Dual learning for joint facial landmark detection and action unit recognition. IEEE Transactions on Affective Computing"},{"issue":"12","key":"5154_CR39","doi-asserted-by":"publisher","first-page":"3539","DOI":"10.1109\/TCSVT.2017.2771150","volume":"28","author":"X Xiang","year":"2017","unstructured":"Xiang X, Tran TD (2017) Linear disentangled representation learning for facial actions. IEEE Transactions on Circuits and Systems for Video Technology 28(12):3539\u20133544","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"5154_CR40","doi-asserted-by":"crossref","unstructured":"Yan J, Wang J, Li Q et\u00a0al (2022) Weakly supervised regional and temporal learning for facial action unit recognition. IEEE Transactions on Multimedia","DOI":"10.1145\/3474085.3475674"},{"key":"5154_CR41","doi-asserted-by":"crossref","unstructured":"Yan J, Wang J, Li Q et\u00a0al (2022) Weakly supervised regional and temporal learning for facial action unit recognition. IEEE Transactions on Multimedia pp 1\u20131","DOI":"10.1145\/3474085.3475674"},{"key":"5154_CR42","doi-asserted-by":"crossref","unstructured":"Yan W, Li S, Que C et\u00a0al (2020) Raf-au database: in-the-wild facial expressions with subjective emotion judgement and objective au annotations. In: Proceedings of the Asian Conference on Computer Vision (ACCV)","DOI":"10.1007\/978-3-030-69544-6_5"},{"key":"5154_CR43","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.patrec.2022.12.001","volume":"165","author":"B Yang","year":"2023","unstructured":"Yang B, Wu J, Ikeda K et al (2023) Deep learning pipeline for spotting macro-and micro-expressions in long video sequences based on action units and optical flow. Pattern Recogn Lett 165:63\u201374","journal-title":"Pattern Recogn Lett"},{"key":"5154_CR44","doi-asserted-by":"crossref","unstructured":"Yang H, Yin L, Zhou Y et\u00a0al (2021) Exploiting semantic embedding and visual feature for facial action unit detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10,482\u201310,491","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"5154_CR45","doi-asserted-by":"crossref","unstructured":"Yang L, Ertugrul IO, Cohn JF et\u00a0al (2019) Facs3d-net: 3d convolution based spatiotemporal representation for action unit detection. In: 2019 8th International conference on affective computing and intelligent interaction (ACII), pp 538\u2013544","DOI":"10.1109\/ACII.2019.8925514"},{"key":"5154_CR46","doi-asserted-by":"crossref","unstructured":"Yao G, Yuan Y, Shao T et\u00a0al (2021) One-shot face reenactment using appearance adaptive normalization. In: Proceedings of the AAAI conference on artificial intelligence, pp 3172\u20133180","DOI":"10.1609\/aaai.v35i4.16427"},{"key":"5154_CR47","doi-asserted-by":"crossref","unstructured":"You R, Guo Z, Cui L et\u00a0al (2020) Cross-modality attention with semantic graph embedding for multi-label classification. In: Proceedings of the AAAI conference on artificial intelligence, pp 12,709\u201312,716","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"5154_CR48","doi-asserted-by":"crossref","unstructured":"Zhang W, Ji X, Chen K et\u00a0al (2021) Learning a facial expression embedding disentangled from identity. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6759\u20136768","DOI":"10.1109\/CVPR46437.2021.00669"},{"issue":"10","key":"5154_CR49","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, Yin L, Cohn JF et al (2014) Bp4d-spontaneous: a high-resolution spontaneous 3d dynamic facial expression database. Image and Vision Computing 32(10):692\u2013706","journal-title":"Image and Vision Computing"},{"key":"5154_CR50","doi-asserted-by":"crossref","unstructured":"Zhang Z, Girard JM, Wu Y et\u00a0al (2016) Multimodal spontaneous emotion corpus for human behavior analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3438\u20133446","DOI":"10.1109\/CVPR.2016.374"},{"key":"5154_CR51","doi-asserted-by":"crossref","unstructured":"Zhao K, Chu WS, De\u00a0la Torre F et\u00a0al (2015) 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","DOI":"10.1109\/CVPR.2015.7298833"},{"key":"5154_CR52","doi-asserted-by":"crossref","unstructured":"Zhao K, Chu WS, Martinez AM (2018) Learning facial action units from web images with scalable weakly supervised clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2090\u20132099","DOI":"10.1109\/CVPR.2018.00223"},{"issue":"5","key":"5154_CR53","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1007\/s00371-019-01707-5","volume":"36","author":"R Zhi","year":"2020","unstructured":"Zhi R, Liu M, Zhang D (2020) A comprehensive survey on automatic facial action unit analysis. The Visual Computer 36(5):1067\u20131093","journal-title":"The Visual Computer"},{"issue":"8","key":"5154_CR54","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/TCYB.2014.2354351","volume":"45","author":"L Zhong","year":"2015","unstructured":"Zhong L, Liu Q, Yang P et al (2015) Learning multiscale active facial patches for expression analysis. IEEE Transactions on Cybernetics 45(8):1499\u20131510","journal-title":"IEEE Transactions on Cybernetics"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-05154-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-05154-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-05154-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T14:58:22Z","timestamp":1730991502000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-05154-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["5154"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-05154-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2 November 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval:"}}]}}