{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T06:19:16Z","timestamp":1777357156049,"version":"3.51.4"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T00:00:00Z","timestamp":1535068800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61370229"],"award-info":[{"award-number":["61370229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the GDUPS"},{"name":"the CSC","award":["201706755023"],"award-info":[{"award-number":["201706755023"]}]},{"DOI":"10.13039\/501100002858","name":"the China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2016M600657"],"award-info":[{"award-number":["2016M600657"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"the China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2017T100637"],"award-info":[{"award-number":["2017T100637"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1007\/s11042-018-6555-7","type":"journal-article","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T13:07:01Z","timestamp":1535116021000},"page":"30651-30675","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-modal multi-concept-based deep neural network for automatic image annotation"],"prefix":"10.1007","volume":"78","author":[{"given":"Haijiao","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1371-2608","authenticated-orcid":false,"given":"Changqin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muxiong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,24]]},"reference":[{"issue":"3","key":"6555_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2(3):1\u201327","journal-title":"ACM Trans Intell Syst Technol"},{"key":"6555_CR2","unstructured":"Chen M, Zheng A, Weinberger KQ (2013) Fast image tagging. In: Proceedings of ACM International Conference on Machine Learning, pp 1274\u20131282"},{"key":"6555_CR3","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1016\/j.neucom.2017.09.048","volume":"275","author":"W Chu","year":"2018","unstructured":"Chu W, Cai D (2018) Deep feature based contextual model for object detection. Neurocomputing 275:1035\u20131042","journal-title":"Neurocomputing"},{"key":"6555_CR4","doi-asserted-by":"crossref","unstructured":"Chua TS, Tang J, Hong R, Li H, Luo Z, Zheng Y (2009) NUS-WIDE: a real-world Web image database from National University of Singapore. In: Proceedings of ACM International Conference on Image and Video Retrieval, pp 48\u201356","DOI":"10.1145\/1646396.1646452"},{"key":"6555_CR5","unstructured":"Gong Y, Jia Y, Leung T, Toshev A, Ioffe S (2014) Deep convolutional ranking for multilabel image annotation. In: Proceedings of International Conference on Learning Representations"},{"key":"6555_CR6","doi-asserted-by":"crossref","unstructured":"Guillaumin M, Mensink T, Verbeek J, Schmid C (2009) TagProp: discriminative metric learning in nearest neighbor models for image auto-annotation. In: Proceedings of IEEE International Conference on Computer Vision, pp 309\u2013316","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"6555_CR7","doi-asserted-by":"crossref","unstructured":"Guillaumin M, Verbeek J, Schmid C (2010) Multimodal semi-supervised learning for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 902\u2013909","DOI":"10.1109\/CVPR.2010.5540120"},{"key":"6555_CR8","doi-asserted-by":"crossref","unstructured":"Izadinia H, Russell BC, Farhadi A, Hoffman MD, Hertzmann A (2015) Deep classifiers from image tags in the wild. In: Proceedings of ACM Conference on Multimedia, pp 13\u201318","DOI":"10.1145\/2814815.2814821"},{"key":"6555_CR9","doi-asserted-by":"crossref","unstructured":"Kalayeh MM, Idrees H, Shah M (2014) NMF-KNN: image annotation using weighted multi-view non-negative matrix factorization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 184\u2013191","DOI":"10.1109\/CVPR.2014.31"},{"key":"6555_CR10","doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of ACL International Conference on Empirical Methods in Natural Language Processing, pp 1746\u20131751","DOI":"10.3115\/v1\/D14-1181"},{"issue":"6","key":"6555_CR11","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1109\/TIP.2016.2545300","volume":"25","author":"H Lai","year":"2016","unstructured":"Lai H, Pan Y, Shu X, Wei Y, Yan S (2016) Instance-aware hashing for multi-label image retrieval. IEEE Trans Image Process 25(6):2469\u20132479","journal-title":"IEEE Trans Image Process"},{"issue":"7553","key":"6555_CR12","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"6555_CR13","doi-asserted-by":"crossref","unstructured":"Li Y, Song Y, Luo J (2017) Improving pairwise ranking for multi-label image classification. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp 426\u2013435","DOI":"10.1109\/CVPR.2017.199"},{"key":"6555_CR14","unstructured":"Lin M, Chen Q, Yan S (2014) Network In Network. In: Proceedings of International Conference on Learning Representations"},{"key":"6555_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patcog.2017.03.014","volume":"68","author":"G Lin","year":"2017","unstructured":"Lin G, Liao K, Sun B, Chen Y, Zhao F (2017) Dynamic graph fusion label propagation for semi-supervised multi-modality classification. Pattern Recogn 68:14\u201323","journal-title":"Pattern Recogn"},{"key":"6555_CR16","doi-asserted-by":"crossref","unstructured":"Liu W, Tsang IW (2015) Large margin metric learning for multi-label prediction. In: Proceedings of AAAI Conference on Artificial Intelligence, pp 2800\u20132806","DOI":"10.1609\/aaai.v29i1.9610"},{"key":"6555_CR17","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.eswa.2018.03.014","volume":"104","author":"Z Liu","year":"2018","unstructured":"Liu Z, Zhang C, Chen C (2018) MMDF-LDA: an improved multi-modal latent Dirichlet allocation model for social image annotation. Expert Syst Appl 104:168\u2013184","journal-title":"Expert Syst Appl"},{"key":"6555_CR18","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of Advances in Neural Information Processing Systems, pp 3111\u20133119"},{"issue":"7","key":"6555_CR19","doi-asserted-by":"publisher","first-page":"4083","DOI":"10.1007\/s11042-015-3087-2","volume":"75","author":"K Nogueira","year":"2016","unstructured":"Nogueira K, Veloso AA, Santos JAD (2016) Pointwise and pairwise clothing annotation: combining features from social media. Multimed Tools Appl 75(7):4083\u20134113","journal-title":"Multimed Tools Appl"},{"key":"6555_CR20","unstructured":"Nowak S, Nagel K, Liebetrau J (2011) The CLEF 2011 photo annotation and concept-based retrieval tasks. In: Proceedings of CLEF Conference and Labs of the Evaluation Forum, pp 1\u201325"},{"key":"6555_CR21","unstructured":"Ren Z, Jin H, Lin Z, Fang C, Yuille A (2015) Multi-instance visual-semantic embedding. arXiv: 1512.06963"},{"key":"6555_CR22","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.neucom.2015.05.090","volume":"168","author":"X Shu","year":"2015","unstructured":"Shu X, Lai D, Xu H, Tao L (2015) Learning shared subspace for multi-label dimensionality reduction via dependence maximization. Neurocomputing 168:356\u2013364","journal-title":"Neurocomputing"},{"key":"6555_CR23","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations"},{"key":"6555_CR24","unstructured":"Song Y, Mcduff D, Vasisht D, Kapoor A (2016) Exploiting sparsity and co-occurrence structure for action unit recognition. In: Proceedings of IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, pp 1\u20138"},{"issue":"1","key":"6555_CR25","first-page":"2949","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Salakhutdinov R (2014) Multimodal learning with deep Boltzmann machines. J Mach Learn Res 15(1):2949\u20132980","journal-title":"J Mach Learn Res"},{"key":"6555_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6555_CR27","doi-asserted-by":"crossref","unstructured":"Wang Y, Lin X, Wu L, Zhang W, Zhang Q (2015) LBMCH: learning bridging mapping for cross-modal hashing. In: Proceedings of International ACM SIGIR, pp 999\u20131002","DOI":"10.1145\/2766462.2767825"},{"issue":"11","key":"6555_CR28","doi-asserted-by":"publisher","first-page":"3939","DOI":"10.1109\/TIP.2015.2457339","volume":"24","author":"Y Wang","year":"2015","unstructured":"Wang Y, Lin X, Wu L, Zhang W, Zhang Q, Huang X (2015) Robust subspace clustering for multi-view data by exploiting correlation consensus. IEEE Trans Image Process 24(11):3939\u20133949","journal-title":"IEEE Trans Image Process"},{"key":"6555_CR29","unstructured":"Wang Y, Zhang W, Wu L, Lin X, Fang M, Pan S (2016) Iterative views agreement: an iterative low-rank based structured optimization method to multi-view spectral clustering. In: Proceedings of International Joint Conference on Artificial Intelligence, pp 2153\u20132159"},{"issue":"1","key":"6555_CR30","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1109\/TNNLS.2015.2498149","volume":"28","author":"Y Wang","year":"2017","unstructured":"Wang Y, Zhang W, Wu L, Lin X, Zhao X (2017) Unsupervised metric fusion over multiview data by graph random walk-based cross-view diffusion. IEEE Trans Neural Netw Learn Syst 28(1):57\u201370","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"6555_CR31","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.1109\/TIP.2017.2655449","volume":"26","author":"Y Wang","year":"2017","unstructured":"Wang Y, Lin X, Wu L, Zhang W (2017) Effective multi-query expansions: collaborative deep networks for robust landmark retrieval. IEEE Trans Image Process 26(3):1393\u20131404","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"6555_CR32","doi-asserted-by":"publisher","first-page":"4833","DOI":"10.1109\/TNNLS.2017.2777489","volume":"29","author":"Yang Wang","year":"2018","unstructured":"Wang Y, Wu L, Lin X, Gao J (2018) Multiview spectral clustering via structured low-rank matrix factorization. IEEE Transactions on Neural Networks and Learning Systems, https:\/\/doi.org\/10.1109\/TNNLS.2017.2777489","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"6555_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2018.03.006","volume":"103","author":"Y Wang","year":"2018","unstructured":"Wang Y, Wu L (2018) Beyond low-rank representations: orthogonal clustering basis reconstruction with optimized graph structure for multi-view spectral clustering. Neural Netw 103:1\u20138","journal-title":"Neural Netw"},{"issue":"8","key":"6555_CR34","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1007\/s11263-018-1085-3","volume":"126","author":"B Wu","year":"2018","unstructured":"Wu B, Jia F, Liu W, Ghanem B, Lyu S (2018) Multi-label learning with missing labels using mixed dependency graphs. International Journal of Computer Vision 126(8):875\u2013896","journal-title":"International Journal of Computer Vision"},{"key":"6555_CR35","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/j.patcog.2017.10.004","volume":"76","author":"L Wu","year":"2018","unstructured":"Wu L, Wang Y, Li X, Gao J (2018) What-and-where to match: deep spatially multiplicative integration networks for person re-identification. Pattern Recogn 76:727\u2013738","journal-title":"Pattern Recogn"},{"issue":"5","key":"6555_CR36","doi-asserted-by":"publisher","first-page":"1791","DOI":"10.1109\/TCYB.2018.2813971","volume":"49","author":"Lin Wu","year":"2019","unstructured":"Wu L, Wang Y, Li X, Gao J (2018) Deep attention-based spatially recursive networks for fine-grained visual recognition. IEEE Transactions on Cybernetics. https:\/\/doi.org\/10.1109\/TCYB.2018.2813971","journal-title":"IEEE Transactions on Cybernetics"},{"key":"6555_CR37","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.patcog.2017.08.029","volume":"73","author":"L Wu","year":"2018","unstructured":"Wu L, Wang Y, Gao J, Li X (2018) Deep adaptive feature embedding with local sample distributions for person re-identification. Pattern Recogn 73:275\u2013288","journal-title":"Pattern Recogn"},{"key":"6555_CR38","doi-asserted-by":"crossref","unstructured":"Xiang Y, Zhou X, Liu Z, Chua TS, Ngo CW (2010) Semantic context modeling with maximal margin conditional random fields for automatic image annotation. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp 3368\u20133375","DOI":"10.1109\/CVPR.2010.5540015"},{"issue":"2","key":"6555_CR39","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s11042-014-2018-y","volume":"74","author":"L Xie","year":"2015","unstructured":"Xie L, Pan P, Lu Y (2015) Markov random field based fusion for supervised and semi-supervised multi-modal image classification. Multimed Tools Appl 74(2):613\u2013634","journal-title":"Multimed Tools Appl"},{"issue":"12","key":"6555_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-015-5486-4","volume":"58","author":"H Xu","year":"2015","unstructured":"Xu H, Huang C, Pan P, Zhao G, Xu C, Lu Y, Chen D, Wu J (2015) Image retrieval based on multi-concept detector and semantic correlation. Sci China Inf Sci 58(12):1\u201315","journal-title":"Sci China Inf Sci"},{"issue":"12","key":"6555_CR41","doi-asserted-by":"publisher","first-page":"2273","DOI":"10.1109\/TCSVT.2015.2477937","volume":"26","author":"C Xu","year":"2016","unstructured":"Xu C, Lu C, Liang X, Gao J, Zheng W, Wang T, Yan S (2016) Multi-loss Regularized Deep Neural Network. IEEE Trans Circ Syst Video Technol 26 (12):2273\u20132283","journal-title":"IEEE Trans Circ Syst Video Technol"},{"issue":"3","key":"6555_CR42","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1109\/TSMCB.2011.2179533","volume":"42","author":"S Zhang","year":"2012","unstructured":"Zhang S, Huang J, Li H, Metaxas D (2012) Automatic image annotation and retrieval using group sparsity. IEEE Trans Syst Man Cybern Part B: Cybern 42 (3):838\u2013849","journal-title":"IEEE Trans Syst Man Cybern Part B: Cybern"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6555-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6555-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6555-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T05:53:49Z","timestamp":1661838829000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6555-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,24]]},"references-count":42,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["6555"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6555-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,24]]},"assertion":[{"value":"1 June 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}