{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:17:08Z","timestamp":1769822228653,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031189067","type":"print"},{"value":"9783031189074","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-18907-4_50","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"645-659","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Prior-Guided Multi-scale Fusion Transformer for\u00a0Face Attribute Recognition"],"prefix":"10.1007","author":[{"given":"Shaoheng","family":"Song","sequence":"first","affiliation":[]},{"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jiaxiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Aihua","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"50_CR1","doi-asserted-by":"crossref","unstructured":"Cao, J., Li, Y., Zhang, Z.: Partially shared multi-task convolutional neural network with local constraint for face attribute learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4290\u20134299 (2018)","DOI":"10.1109\/CVPR.2018.00451"},{"issue":"5","key":"50_CR2","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1109\/TMM.2013.2242460","volume":"15","author":"BC Chen","year":"2013","unstructured":"Chen, B.C., Chen, Y.Y., Kuo, Y.H., Hsu, W.H.: Scalable face image retrieval using attribute-enhanced sparse codewords. IEEE Trans. Multimedia 15(5), 1163\u20131173 (2013). https:\/\/doi.org\/10.1109\/TMM.2013.2242460","journal-title":"IEEE Trans. Multimedia"},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177\u20135186 (2019)","DOI":"10.1109\/CVPR.2019.00532"},{"key":"50_CR4","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. arXiv preprint arXiv:2107.00652 (2021)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"50_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Hand, E.M., Chellappa, R.: Attributes for improved attributes: a multi-task network utilizing implicit and explicit relationships for facial attribute classification. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11229"},{"key":"50_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":"50_CR8","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Harnessing synthesized abstraction images to improve facial attribute recognition. In: IJCAI, pp. 733\u2013740 (2018)","DOI":"10.24963\/ijcai.2018\/102"},{"key":"50_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Wang, Z., Fu, Y., Feng, R., Jiang, Y.G., Xue, X.: Adaptively weighted multi-task deep network for person attribute classification. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1636\u20131644 (2017)","DOI":"10.1145\/3123266.3123424"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Kalayeh, M.M., Gong, B., Shah, M.: Improving facial attribute prediction using semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.450"},{"key":"50_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"50_CR12","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"50_CR13","unstructured":"Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188\u20131196. PMLR (2014)"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"50_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.425"},{"key":"50_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"50_CR17","doi-asserted-by":"crossref","unstructured":"Lu, Y., Kumar, A., Zhai, S., Cheng, Y., Javidi, T., Feris, R.: Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5334\u20135343 (2017)","DOI":"10.1109\/CVPR.2017.126"},{"key":"50_CR18","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML (2013)"},{"key":"50_CR19","unstructured":"Mao, L., Yan, Y., Xue, J.H., Wang, H.: Deep multi-task multi-label CNN for effective facial attribute classification. IEEE Trans. Affect. Comput. (2020)"},{"key":"50_CR20","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"50_CR21","doi-asserted-by":"publisher","first-page":"85500","DOI":"10.1109\/ACCESS.2019.2925503","volume":"7","author":"F Nian","year":"2019","unstructured":"Nian, F., Chen, X., Yang, S., Lv, G.: Facial attribute recognition with feature decoupling and graph convolutional networks. IEEE Access 7, 85500\u201385512 (2019)","journal-title":"IEEE Access"},{"key":"50_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/978-3-319-46454-1_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"EM Rudd","year":"2016","unstructured":"Rudd, E.M., G\u00fcnther, M., Boult, T.E.: MOON: a mixed objective optimization network for the recognition of facial attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 19\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_2"},{"key":"50_CR23","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"50_CR24","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.patrec.2018.03.010","volume":"119","author":"A Sethi","year":"2019","unstructured":"Sethi, A., Singh, M., Singh, R., Vatsa, M.: Residual Codean autoencoder for facial attribute analysis. Pattern Recogn. Lett. 119, 157\u2013165 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"50_CR25","doi-asserted-by":"crossref","unstructured":"Shu, Y., Yan, Y., Chen, S., Xue, J.H., Shen, C., Wang, H.: Learning spatial-semantic relationship for facial attribute recognition with limited labeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11916\u201311925 (2021)","DOI":"10.1109\/CVPR46437.2021.01174"},{"key":"50_CR26","unstructured":"Tao, A., Sapra, K., Catanzaro, B.: Hierarchical multi-scale attention for semantic segmentation. arXiv preprint arXiv:2005.10821 (2020)"},{"key":"50_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"50_CR28","unstructured":"Wang, W., et al.: Pvtv 2: improved baselines with pyramid vision transformer. arXiv preprint arXiv:2106.13797 (2021)"},{"key":"50_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., Ye, Y., Gupta, A.: Zero-shot recognition via semantic embeddings and knowledge graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6857\u20136866 (2018)","DOI":"10.1109\/CVPR.2018.00717"},{"key":"50_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Multi-label classification with label graph superimposing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12265\u201312272 (2020)","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"50_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., He, K., Fu, Y., Feng, R., Jiang, Y.G., Xue, X.: Multi-task deep neural network for joint face recognition and facial attribute prediction. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. pp. 365\u2013374 (2017)","DOI":"10.1145\/3078971.3078973"},{"key":"50_CR32","unstructured":"Wu, L., Sun, P., Hong, R., Fu, Y., Wang, X., Wang, M.: SocialGCN: an efficient graph convolutional network based model for social recommendation. arXiv preprint arXiv:1811.02815 (2018)"},{"key":"50_CR33","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Hierarchical feature embedding for attribute recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13055\u201313064 (2020)","DOI":"10.1109\/CVPR42600.2020.01307"},{"key":"50_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107155","volume":"100","author":"X Zheng","year":"2020","unstructured":"Zheng, X., Huang, H., Guo, Y., Wang, B., He, R.: Blan: bi-directional ladder attentive network for facial attribute prediction. Pattern Recogn. 100, 107155 (2020)","journal-title":"Pattern Recogn."},{"key":"50_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Sullivan, J., Li, H.: Leveraging mid-level deep representations for predicting face attributes in the wild. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3239\u20133243. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532958"},{"key":"50_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: Mucko: multi-layer cross-modal knowledge reasoning for fact-based visual question answering. arXiv preprint arXiv:2006.09073 (2020)","DOI":"10.24963\/ijcai.2020\/153"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:13:06Z","timestamp":1666825986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.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":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}