{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:16:31Z","timestamp":1759133791659,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"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":["Appl Intell"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s10489-021-02755-y","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:02:25Z","timestamp":1631059345000},"page":"6354-6375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Lightweight network architecture using difference saliency maps for facial action unit detection"],"prefix":"10.1007","volume":"52","author":[{"given":"Jing","family":"Chen","sequence":"first","affiliation":[]},{"given":"Chenhui","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2912-8994","authenticated-orcid":false,"given":"Kejun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Meichen","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"key":"2755_CR1","doi-asserted-by":"publisher","unstructured":"Benitez-Quiroz CF, Srinivasan R, Martinez AM (2016) Emotionet: An accurate, real-time algorithm for the automatic annotation of a million facial expressions in the wild. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 5562\u20135570. https:\/\/doi.org\/10.1109\/CVPR.2016.600","DOI":"10.1109\/CVPR.2016.600"},{"key":"2755_CR2","doi-asserted-by":"publisher","unstructured":"Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM international conference on image and video retrieval, CIVR \u201907, pp 401\u2013408, Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1282280.1282340","DOI":"10.1145\/1282280.1282340"},{"key":"2755_CR3","doi-asserted-by":"crossref","unstructured":"Corneanu C, Madadi M, Escalera S (2018) Deep structure inference network for facial action unit recognition. In: Proceedings of the european conference on computer vision (ECCV), pp. 298\u2013313","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"2755_CR4","doi-asserted-by":"publisher","unstructured":"Eleftheriadis S, Rudovic O, Pantic M (2015) Multi-conditional latent variable model for joint facial action unit detection. In: 2015 IEEE international conference on computer vision (ICCV), pp 3792\u20133800. https:\/\/doi.org\/10.1109\/ICCV.2015.432","DOI":"10.1109\/ICCV.2015.432"},{"key":"2755_CR5","doi-asserted-by":"crossref","unstructured":"Friesen E, Ekman P (1978) Facial action coding system: a technique for the measurement of facial movement. Palo Alto 3","DOI":"10.1037\/t27734-000"},{"key":"2755_CR6","unstructured":"Friesen E, Ekman P (2002) Facial action coding system(facs). A human face"},{"key":"2755_CR7","doi-asserted-by":"crossref","unstructured":"Gupta V, Raman S (2017) Automatic trimap generation for image matting. In: 2016 International conference on signal and information processing (IConSIP)","DOI":"10.1109\/ICONSIP.2016.7857477"},{"key":"2755_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (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"},{"issue":"8","key":"2755_CR9","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011\u20132023. https:\/\/doi.org\/10.1109\/TPAMI.2019.2913372","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2755_CR10","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"2755_CR11","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR, pp 448\u2013456"},{"issue":"11","key":"2755_CR12","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254\u20131259. https:\/\/doi.org\/10.1109\/34.730558","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2755_CR13","doi-asserted-by":"publisher","unstructured":"Jaiswal S, Valstar M (2016) Deep learning the dynamic appearance and shape of facial action units. In: 2016 IEEE winter conference on applications of computer vision (WACV), pp 1\u20138. https:\/\/doi.org\/10.1109\/WACV.2016.7477625","DOI":"10.1109\/WACV.2016.7477625"},{"key":"2755_CR14","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King DE (2009) Dlib-ml: A machine learning toolkit. J Mach Learn Res 10:1755\u20131758","journal-title":"J Mach Learn Res"},{"key":"2755_CR15","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International conference on learning representations (ICLR)"},{"key":"2755_CR16","doi-asserted-by":"publisher","unstructured":"Li W, Abtahi F, Zhu Z (2017) Action unit detection with region adaptation, multi-labeling learning and optimal temporal fusing. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 6766\u20136775. https:\/\/doi.org\/10.1109\/CVPR.2017.716","DOI":"10.1109\/CVPR.2017.716"},{"key":"2755_CR17","doi-asserted-by":"publisher","unstructured":"Li W, Abtahi F, Zhu Z, Yin L (2017) Eac-net: A region-based deep enhancing and cropping approach for facial action unit detection. In: 2017 12th IEEE international conference on automatic face gesture recognition (FG 2017), pp 103\u2013110. https:\/\/doi.org\/10.1109\/FG.2017.136","DOI":"10.1109\/FG.2017.136"},{"issue":"11","key":"2755_CR18","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 (2018) Eac-net: Deep nets with enhancing and cropping for facial action unit detection. IEEE Trans Pattern Anal Mach Intell 40(11):2583\u20132596. https:\/\/doi.org\/10.1109\/TPAMI.2018.2791608","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"2755_CR19","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1007\/s10489-020-01907-w","volume":"51","author":"M Liu","year":"2021","unstructured":"Liu M, Yan X, Wang C, Wang K (2021) Segmentation mask-guided person image generation. Appl Intell 51(2):1161\u20131176. https:\/\/doi.org\/10.1007\/s10489-020-01907-w","journal-title":"Appl Intell"},{"key":"2755_CR20","doi-asserted-by":"crossref","unstructured":"Liu Z, Dong J, Zhang C, Wang L, Dang J (2020) Relation modeling with graph convolutional networks for facial action unit detection. In: International conference on multimedia modeling. Springer, pp 489\u2013501","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"2755_CR21","doi-asserted-by":"crossref","unstructured":"Lucey P, Cohn JF, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expression. In: 2010 ieee computer society conference on computer vision and pattern recognition-workshops. IEEE, pp 94\u2013101","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"2755_CR22","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. https:\/\/doi.org\/10.1016\/j.neucom.2019.03.082","journal-title":"Neurocomputing"},{"key":"2755_CR23","doi-asserted-by":"publisher","unstructured":"Mavadati M, Sanger P, Mahoor MH (2016) Extended disfa dataset: Investigating posed and spontaneous facial expressions. In: 2016 IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 1452\u20131459. https:\/\/doi.org\/10.1109\/CVPRW.2016.182","DOI":"10.1109\/CVPRW.2016.182"},{"issue":"7","key":"2755_CR24","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971\u2013987. https:\/\/doi.org\/10.1109\/TPAMI.2002.1017623","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2755_CR25","doi-asserted-by":"crossref","unstructured":"Shao Z, Liu Z, Cai J, Ma L (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. DOI10.1007\/978-3-030-01261-8_43","DOI":"10.1007\/978-3-030-01261-8_43"},{"issue":"2","key":"2755_CR26","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 (2021) J\u00c2A-Net: joint facial action unit detection and face alignment via adaptive attention. Int J Comput Vis 129(2):321\u2013340. https:\/\/doi.org\/10.1007\/s11263-020-01378-z","journal-title":"Int J Comput Vis"},{"key":"2755_CR27","doi-asserted-by":"publisher","unstructured":"Shao Z, Liu Z, Cai J, Wu Y, Ma L (2019) Facial action unit detection using attention and relation learning. IEEE Trans Affect Comput 1\u20131. https:\/\/doi.org\/10.1109\/TAFFC.2019.2948635","DOI":"10.1109\/TAFFC.2019.2948635"},{"issue":"4","key":"2755_CR28","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640\u2013651. https:\/\/doi.org\/10.1109\/TPAMI.2016.2572683","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2755_CR29","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd International conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. arXiv:1409.1556"},{"key":"2755_CR30","doi-asserted-by":"publisher","unstructured":"Song Y, McDuff D, Vasisht D, Kapoor A (2015) Exploiting sparsity and co-occurrence structure for action unit recognition. In: 2015 11th IEEE international conference and workshops on automatic face and gesture recognition (FG), vol 1, pp 1\u20138. https:\/\/doi.org\/10.1109\/FG.2015.7163081","DOI":"10.1109\/FG.2015.7163081"},{"issue":"8","key":"2755_CR31","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.1080\/01431161.2020.1826059","volume":"42","author":"Z Song","year":"2021","unstructured":"Song Z, Sui H, Hua L (2021) A hierarchical object detection method in large-scale optical remote sensing satellite imagery using saliency detection and CNN. Int J Remote Sens 42(8):2827\u20132847. https:\/\/doi.org\/10.1080\/01431161.2020.1826059","journal-title":"Int J Remote Sens"},{"key":"2755_CR32","doi-asserted-by":"publisher","unstructured":"Valstar MF, Almaev T, Girard JM, McKeown G, Mehu M, Yin L, Pantic M, Cohn JF (2015) 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 06, pp 1\u20138. https:\/\/doi.org\/10.1109\/FG.2015.7284874https:\/\/doi.org\/10.1109\/FG.2015.7284874","DOI":"10.1109\/FG.2015.7284874 10.1109\/FG.2015.7284874"},{"issue":"7","key":"2755_CR33","first-page":"12,128","volume":"34","author":"B Wang","year":"2020","unstructured":"Wang B, Chen Q, Zhou M, Zhang Z, Gai K (2020) Progressive feature polishing network for salient object detection. Proc AAAI Conf Artif Intell 34(7):12,128\u201312,135","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"3","key":"2755_CR34","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1109\/TAFFC.2017.2737540","volume":"10","author":"S Wang","year":"2019","unstructured":"Wang S, Wu S, Peng G, Ji Q (2019) Capturing feature and label relations simultaneously for multiple facial action unit recognition. IEEE Trans Affect Comput 10(3):348\u2013359. https:\/\/doi.org\/10.1109\/TAFFC.2017.2737540","journal-title":"IEEE Trans Affect Comput"},{"key":"2755_CR35","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.neucom.2019.05.018","volume":"359","author":"SJ Wang","year":"2019","unstructured":"Wang SJ, Lin B, Wang Y, Yi T, Zou B, wen Lyu X (2019) Action units recognition based on deep spatial-convolutional and multi-label residual network. Neurocomputing 359:130\u2013138. https:\/\/doi.org\/10.1016\/j.neucom.2019.05.018","journal-title":"Neurocomputing"},{"key":"2755_CR36","doi-asserted-by":"publisher","unstructured":"Wang Z, Li Y, Wang S, Ji Q (2013) Capturing global semantic relationships for facial action unit recognition. In: 2013 IEEE international conference on computer vision, pp 3304\u20133311. https:\/\/doi.org\/10.1109\/ICCV.2013.410","DOI":"10.1109\/ICCV.2013.410"},{"key":"2755_CR37","doi-asserted-by":"publisher","unstructured":"Zhang T, Qi G, Xiao B, Wang J (2017) Interleaved group convolutions. In: 2017 IEEE International conference on computer vision (ICCV), pp 4383\u20134392. https:\/\/doi.org\/10.1109\/ICCV.2017.469","DOI":"10.1109\/ICCV.2017.469"},{"key":"2755_CR38","doi-asserted-by":"publisher","unstructured":"Zhao K, Chu W, Zhang H (2016) Deep region and multi-label learning for facial action unit detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 3391\u20133399. https:\/\/doi.org\/10.1109\/CVPR.2016.369","DOI":"10.1109\/CVPR.2016.369"},{"issue":"8","key":"2755_CR39","doi-asserted-by":"publisher","first-page":"3931","DOI":"10.1109\/TIP.2016.2570550","volume":"25","author":"K Zhao","year":"2016","unstructured":"Zhao K, Chu WS, De la Torre F, Cohn JF, Zhang H (2016) Joint patch and multi-label learning for facial action unit and holistic expression recognition. IEEE Trans Image Process 25(8):3931\u20133946. https:\/\/doi.org\/10.1109\/TIP.2016.2570550","journal-title":"IEEE Trans Image Process"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02755-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02755-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02755-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T04:19:20Z","timestamp":1649823560000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02755-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,8]]},"references-count":39,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["2755"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02755-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2021,9,8]]},"assertion":[{"value":"9 August 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}