{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T20:21:42Z","timestamp":1769199702819,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,1,9]],"date-time":"2022-01-09T00:00:00Z","timestamp":1641686400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,9]],"date-time":"2022-01-09T00:00:00Z","timestamp":1641686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20398"],"award-info":[{"award-number":["U20A20398"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076005"],"award-info":[{"award-number":["62076005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906002"],"award-info":[{"award-number":["61906002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085MF191"],"award-info":[{"award-number":["2008085MF191"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085QF306"],"award-info":[{"award-number":["2008085QF306"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province, China","award":["GXXT-2021-002"],"award-info":[{"award-number":["GXXT-2021-002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s12559-021-09977-9","type":"journal-article","created":{"date-parts":[[2022,1,9]],"date-time":"2022-01-09T00:02:42Z","timestamp":1641686562000},"page":"1308-1319","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["An Attention-Driven Multi-label Image Classification with Semantic Embedding and Graph Convolutional Networks"],"prefix":"10.1007","volume":"15","author":[{"given":"Dengdi","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leilei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuanlian","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,9]]},"reference":[{"key":"9977_CR1","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.\u00a02016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"9977_CR2","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556. 2014."},{"key":"9977_CR3","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02016. p. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"9977_CR4","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02017. p. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"9977_CR5","doi-asserted-by":"crossref","unstructured":"Alkhateeb A, Zhou L, Tabl AA, Rueda L. Deep Learning Approach for Breast Cancer InClust 5 Prediction based on Multiomics Data Integration. In: Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics.\u00a02020. p. 1\u20136.","DOI":"10.1145\/3388440.3415992"},{"key":"9977_CR6","doi-asserted-by":"crossref","unstructured":"Wang J, Yang Y, Mao J, Huang Z, Huang C, Xu W. CNN-RNN: A unified framework for multi-label image classification. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02016. p. 2285\u20132294.","DOI":"10.1109\/CVPR.2016.251"},{"key":"9977_CR7","doi-asserted-by":"crossref","unstructured":"Li Q, Qiao M, Bian W, Tao D. Conditional graphical lasso for multi-label image classification. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02016. p. 2977\u20132986.","DOI":"10.1109\/CVPR.2016.325"},{"key":"9977_CR8","unstructured":"Yazici VO, Gonzalez-Garcia A, Ramisa A, Twardowski B, Weijer JVD. Orderless Recurrent Models for Multi-label Classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.\u00a02020. p. 13440\u201313449."},{"key":"9977_CR9","doi-asserted-by":"crossref","unstructured":"Chen ZM, Wei XS, Wang P, Guo Y. Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.\u00a02019. p. 5177\u20135186.","DOI":"10.1109\/CVPR.2019.00532"},{"issue":"9","key":"9977_CR10","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TPAMI.2015.2491929","volume":"38","author":"Y Wei","year":"2015","unstructured":"Wei Y, Xia W, Lin M, Huang J, Ni B, Dong J, et al. HCP: A flexible CNN framework for multi-label image classification. IEEE Trans Pattern Anal Mach Intell. 2015;38(9):1901\u20137.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9977_CR11","doi-asserted-by":"crossref","unstructured":"Wang Z, Chen T, Li G, Xu R, Lin L. Multi-label image recognition by recurrently discovering attentional regions. In: Proceedings of the IEEE International Conference on Computer Vision.\u00a02017. p. 464\u2013472.","DOI":"10.1109\/ICCV.2017.58"},{"key":"9977_CR12","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.\u00a02017. p. 5513\u20135522.","DOI":"10.1109\/CVPR.2017.219"},{"key":"9977_CR13","doi-asserted-by":"crossref","unstructured":"Ge W, Yang S, Yu Y. Multi-evidence filtering and fusion for multi-label classification, object detection and semantic segmentation based on weakly supervised learning. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02018. p. 1277\u20131286.","DOI":"10.1109\/CVPR.2018.00139"},{"key":"9977_CR14","doi-asserted-by":"crossref","unstructured":"Lee CW, Fang W, Yeh CK, Frank\u00a0Wang YC. Multi-label zero-shot learning with structured knowledge graphs. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02018. p. 1576\u20131585.","DOI":"10.1109\/CVPR.2018.00170"},{"key":"9977_CR15","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on Computer Vision and Pattern Recognition. IEEE; 2009. p. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9977_CR16","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, et\u00a0al. Microsoft coco: Common objects in context. In: European conference on computer vision. Springer; 2014. p. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"9977_CR17","doi-asserted-by":"crossref","unstructured":"Chen Q, Song Z, Hua Y, Huang Z, Yan S. Hierarchical matching with side information for image classification. In: 2012 IEEE conference on Computer Vision and Pattern Recognition. IEEE; 2012. p. 3426\u20133433.","DOI":"10.1109\/CVPR.2012.6248083"},{"issue":"3","key":"9977_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2007070101","volume":"3","author":"G Tsoumakas","year":"2007","unstructured":"Tsoumakas G, Katakis I. Multi-label classification: an overview. International Journal of Data Warehousing and Mining (IJDWM). 2007;3(3):1\u201313.","journal-title":"International Journal of Data Warehousing and Mining (IJDWM)"},{"key":"9977_CR19","unstructured":"Gong Y, Jia Y, Leung T, Toshev A, Ioffe S. Deep convolutional ranking for multi-label image annotation. arXiv preprint arXiv:13124894. 2013."},{"key":"9977_CR20","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A. Return of the devil in the details: Delving deep into convolutional nets. arXiv preprint arXiv:14053531. 2014.","DOI":"10.5244\/C.28.6"},{"issue":"3","key":"9977_CR21","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TBDATA.2015.2497270","volume":"1","author":"F Wu","year":"2015","unstructured":"Wu F, Wang Z, Zhang Z, Yang Y, Luo J, Zhu W, et al. Weakly semi-supervised deep learning for multi-label image annotation. IEEE Transactions on Big Data. 2015;1(3):109\u201322.","journal-title":"IEEE Transactions on Big Data"},{"key":"9977_CR22","doi-asserted-by":"crossref","unstructured":"Ghamrawi N, McCallum A. Collective multi-label classification. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management.\u00a02005. p. 195\u2013200.","DOI":"10.1145\/1099554.1099591"},{"key":"9977_CR23","unstructured":"Guo Y, Gu S. Multi-label classification using conditional dependency networks. In: IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol.\u00a022. Citeseer; 2011. p. 1300."},{"key":"9977_CR24","doi-asserted-by":"crossref","unstructured":"Xue X, Zhang W, Zhang J, Wu B, Fan J, Lu Y. Correlative multi-label multi-instance image annotation. In: 2011 International Conference on Computer Vision. IEEE; 2011. p. 651\u2013658.","DOI":"10.1109\/ICCV.2011.6126300"},{"key":"9977_CR25","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.patrec.2017.04.018","volume":"92","author":"AF Tehrani","year":"2017","unstructured":"Tehrani AF, Ahrens D. Modeling label dependence for multi-label classification using the Choquistic regression. Pattern Recogn Lett. 2017;92:75\u201380.","journal-title":"Pattern Recogn Lett"},{"key":"9977_CR26","doi-asserted-by":"crossref","unstructured":"Marino K, Salakhutdinov R, Gupta A. The more you know: Using knowledge graphs for image classification. arXiv preprint arXiv:161204844. 2016.","DOI":"10.1109\/CVPR.2017.10"},{"key":"9977_CR27","doi-asserted-by":"crossref","unstructured":"Wang X, Gupta A. Videos as space-time region graphs. In: Proceedings of the European Conference on Computer Vision (ECCV); 2018. p. 399\u2013417.","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"9977_CR28","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:160902907. 2016."},{"key":"9977_CR29","unstructured":"Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems.\u00a02017. p. 1024\u20131034."},{"key":"9977_CR30","doi-asserted-by":"crossref","unstructured":"Xu J, Tian H, Wang Z, Wang Y, Chen F, Kang W. Joint Input and Output Space Learning for Multi-Label Image Classification. IEEE Trans Multimedia. 2020.","DOI":"10.1109\/TMM.2020.3002185"},{"key":"9977_CR31","unstructured":"Wang Y, Zhang T, Cui Z, Xu C, Yang J. Instance-Aware Graph Convolutional Network for Multi-Label Classification. arXiv preprint arXiv:200808407. 2020."},{"key":"9977_CR32","doi-asserted-by":"crossref","unstructured":"Wang Y, He D, Li F, Long X, Zhou Z, Ma J, et\u00a0al. Multi-label classification with label graph superimposing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034; 2020. p. 12265\u201312272.","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"9977_CR33","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.patrec.2020.07.040","volume":"138","author":"Q Li","year":"2020","unstructured":"Li Q, Peng X, Qiao Y, Peng Q. Learning label correlations for multi-label image recognition with graph networks. Pattern Recogn Lett. 2020;138:378\u201384.","journal-title":"Pattern Recogn Lett"},{"key":"9977_CR34","doi-asserted-by":"crossref","unstructured":"Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, et\u00a0al. Residual attention network for image classification. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition.\u00a02017. p. 3156\u20133164.","DOI":"10.1109\/CVPR.2017.683"},{"key":"9977_CR35","doi-asserted-by":"crossref","unstructured":"Li X, Zhong Z, Wu J, Yang Y, Lin Z, Liu H. Expectation-maximization attention networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision.\u00a02019. p. 9167\u20139176.","DOI":"10.1109\/ICCV.2019.00926"},{"key":"9977_CR36","doi-asserted-by":"crossref","unstructured":"Chu Q, Ouyang W, Li H, Wang X, Liu B, Yu N. Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism. In: Proceedings of the IEEE International Conference on Computer Vision.\u00a02017. p. 4836\u20134845.","DOI":"10.1109\/ICCV.2017.518"},{"key":"9977_CR37","unstructured":"Ba J, Mnih V, Kavukcuoglu K. Multiple object recognition with visual attention. arXiv preprint arXiv:14127755. 2014."},{"key":"9977_CR38","unstructured":"Mnih V, Heess N, Graves A, et\u00a0al. Recurrent models of visual attention. In: Advances in Neural Information Processing Systems.\u00a02014. p. 2204\u20132212."},{"key":"9977_CR39","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, et\u00a0al. Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning.\u00a02015. p. 2048\u20132057."},{"key":"9977_CR40","doi-asserted-by":"crossref","unstructured":"Chen SF, Chen YC, Yeh CK, Wang YCF. Order-free rnn with visual attention for multi-label classification. arXiv preprint arXiv:170705495. 2017.","DOI":"10.1609\/aaai.v32i1.12230"},{"issue":"2","key":"9977_CR41","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW. Selective search for object recognition. Int J Comput Vis. 2013;104(2):154\u201371.","journal-title":"Int J Comput Vis"},{"issue":"5","key":"9977_CR42","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1109\/TPAMI.2017.2707492","volume":"40","author":"Z Zhang","year":"2017","unstructured":"Zhang Z, Liu Y, Chen X, Zhu Y, Cheng MM, Saligrama V, et al. Sequential optimization for efficient high-quality object proposal generation. IEEE Trans Pattern Anal Mach Intell. 2017;40(5):1209\u201323.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9977_CR43","doi-asserted-by":"crossref","unstructured":"Chen T, Xu M, Hui X, Wu H, Lin L. Learning semantic-specific graph representation for multi-label image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision.\u00a02019. p. 522\u2013531.","DOI":"10.1109\/ICCV.2019.00061"},{"issue":"2","key":"9977_CR44","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A. The pascal visual object classes (VOC) challenge. Int J Comput Vis. 2010;88(2):303\u201338.","journal-title":"Int J Comput Vis"},{"key":"9977_CR45","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD. Glove: Global vectors for word representation. In: Proceedings of the 2014\u00a0Conference on Empirical Methods in Natural Language Processing (EMNLP).\u00a02014. p. 1532\u20131543.","DOI":"10.3115\/v1\/D14-1162"},{"issue":"10","key":"9977_CR46","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/TMM.2018.2812605","volume":"20","author":"J Zhang","year":"2018","unstructured":"Zhang J, Wu Q, Shen C, Zhang J, Lu J. Multilabel image classification with regional latent semantic dependencies. IEEE Trans Multimedia. 2018;20(10):2801\u201313.","journal-title":"IEEE Trans Multimedia"},{"key":"9977_CR47","doi-asserted-by":"crossref","unstructured":"Yang H, Tianyi\u00a0Zhou J, Zhang Y, Gao BB, Wu J, Cai J. Exploit bounding box annotations for multi-label object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.\u00a02016. p. 280\u2013288.","DOI":"10.1109\/CVPR.2016.37"},{"key":"9977_CR48","doi-asserted-by":"crossref","unstructured":"Chen T, Wang Z, Li G, Lin L. Recurrent attentional reinforcement learning for multi-label image recognition. arXiv preprint arXiv:171207465. 2017.","DOI":"10.1609\/aaai.v32i1.12281"},{"key":"9977_CR49","unstructured":"Maaten Lvd, Hinton G. Visualizing data using t-SNE.\u00a0J Mach Learn Res.\u00a02008;9(Nov):2579\u20132605."}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-021-09977-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-021-09977-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-021-09977-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T22:33:03Z","timestamp":1726439583000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-021-09977-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,9]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["9977"],"URL":"https:\/\/doi.org\/10.1007\/s12559-021-09977-9","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,9]]},"assertion":[{"value":"25 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2022","order":3,"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":"Ethical Approval"}},{"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":"Informed Consent"}},{"value":"Informed consent was not required as no human or animals were involved.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}