{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:27:10Z","timestamp":1781612830227,"version":"3.54.5"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2017,12,12]],"date-time":"2017-12-12T00:00:00Z","timestamp":1513036800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1007\/s11042-017-5443-x","type":"journal-article","created":{"date-parts":[[2017,12,12]],"date-time":"2017-12-12T06:02:29Z","timestamp":1513058549000},"page":"10251-10271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":116,"title":["CNN-RNN: a large-scale hierarchical image classification framework"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9184-5313","authenticated-orcid":false,"given":"Yanming","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erwin M.","family":"Bakker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael S.","family":"Lew","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,12,12]]},"reference":[{"key":"5443_CR1","unstructured":"Agostinelli F, Hoffman M, Sadowski P, Baldi P (2015) Learning activation functions to improve deep neural networks. In: International conference on learning representations workshops"},{"issue":"3","key":"5443_CR2","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1109\/TPAMI.2013.146","volume":"36","author":"Z Akata","year":"2014","unstructured":"Akata Z, Perronnin F, Harchaoui Z, Schmid C (2014) Good practice in large-scale learning for image classification. IEEE Trans Pattern Anal Mach Intell 36 (3):507\u2013520","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5443_CR3","doi-asserted-by":"crossref","unstructured":"Cao L, Gao L, Song J, Shen F, Wang Y (2017) Multiple hierarchical deep hashing for large scale image retrieval. Multimed Tools Appl 1\u201314","DOI":"10.1007\/s11042-017-4489-0"},{"issue":"1","key":"5443_CR4","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s11263-015-0872-3","volume":"118","author":"M Cimpoi","year":"2016","unstructured":"Cimpoi M, Maji S, Kokkinos I, Vedaldi A (2016) Deep filter banks for texture recognition, description, and segmentation. Int J Comput Vis 118(1):65\u201394","journal-title":"Int J Comput Vis"},{"key":"5443_CR5","unstructured":"Clevert Dj, Unterthiner T, Hochreiter S (2016) Fast and accurate deep network learning by exponential linear units (elus). In: International conference on learning representations"},{"key":"5443_CR6","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Li F-F (2009) Imagenet A large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5443_CR7","doi-asserted-by":"crossref","unstructured":"Deng J, Ding N, Jia Y, Frome A, Murphy K, Bengio S, Li Y, Neven H, Adam H (2014) Large-scale object classification using label relation graphs. In: European conference on computer vision, pp 48\u201364","DOI":"10.1007\/978-3-319-10590-1_4"},{"key":"5443_CR8","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"issue":"2","key":"5443_CR9","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"JL Elman","year":"1990","unstructured":"Elman JL (1990) Finding structure in time. Cogn Sci 14(2):179\u2013211","journal-title":"Cogn Sci"},{"key":"5443_CR10","doi-asserted-by":"crossref","unstructured":"Guo Y, Lew MS (2016) Bag of surrogate parts: one inherent feature of deep cnns. In: British machine vision conference","DOI":"10.5244\/C.30.96"},{"key":"5443_CR11","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","volume":"187","author":"Y Guo","year":"2016","unstructured":"Guo Y, Liu Y, Oerlemans A, Lao S, Song W, Lew MS (2016) Deep learning for visual understanding: a review. Neurocomputing 187:27\u201348","journal-title":"Neurocomputing"},{"key":"5443_CR12","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"},{"key":"5443_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision, pp 630\u2013645","DOI":"10.1007\/978-3-319-46493-0_38"},{"issue":"8","key":"5443_CR14","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"5443_CR15","doi-asserted-by":"crossref","unstructured":"Huang G, Sun Y, Liu Z, Sedra D, Weinberger KQ (2016) Deep networks with stochastic depth. In: European conference on computer vision, pp 646\u2013661","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"5443_CR16","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM international conference on multimedia, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"5443_CR17","doi-asserted-by":"crossref","unstructured":"Jin X, Chunyan X, Feng J, Wei Y, Xiong J, Yan S (2016) Deep learning with s-shaped rectified linear activation units. In: AAAI, pp 1737\u20131743","DOI":"10.1609\/aaai.v30i1.10287"},{"key":"5443_CR18","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images"},{"key":"5443_CR19","unstructured":"Larsson G, Maire M, Shakhnarovich G (2017) Fractalnet: ultra-deep neural networks without residuals. In: International conference on learning representations"},{"key":"5443_CR20","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2169\u20132178","DOI":"10.1109\/CVPR.2006.68"},{"key":"5443_CR21","unstructured":"Lee C-Y, Xie S, Gallagher P, Zhang Z, Zhuowen T (2015) Deeply-supervised nets. In: Artificial intelligence and statistics, pp 562\u2013570"},{"key":"5443_CR22","unstructured":"Li H, Ouyang W, Wang X (2016) Multi-bias non-linear activation in deep neural networks. In: International conference on machine learning, pp 221\u2013229"},{"key":"5443_CR23","doi-asserted-by":"crossref","unstructured":"Liang M, Xiaolin H (2015) Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3367\u20133375","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"5443_CR24","doi-asserted-by":"crossref","unstructured":"Liu Y, Guo Y, Song W, Lew MS (2015) Deepindex for accurate and efficient image retrieval. In: Proceedings of the ACM on international conference on multimedia retrieval, pp 43\u201350","DOI":"10.1145\/2671188.2749300"},{"key":"5443_CR25","doi-asserted-by":"crossref","unstructured":"Liu Y, Guo Y, Lew MS (2017) On the exploration of convolutional fusion networks for visual recognition. In: International conference on multimedia modeling, pp 277\u2013289","DOI":"10.1007\/978-3-319-51811-4_23"},{"key":"5443_CR26","doi-asserted-by":"crossref","unstructured":"Mensink T, Verbeek J, Perronnin F, Csurka G (2013) Distance-based image classification: feneralizing to new classes at near-zero cost, vol 35","DOI":"10.1109\/TPAMI.2013.83"},{"issue":"11","key":"5443_CR27","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller GA (1995) Wordnet: a lexical database for english. Commun ACM 38 (11):39\u201341","journal-title":"Commun ACM"},{"key":"5443_CR28","unstructured":"Mishkin D, Matas J (2016) All you need is a good init. In: International conference on learning representations"},{"key":"5443_CR29","doi-asserted-by":"crossref","unstructured":"Murdock C, Li Z, Zhou H, Duerig T (2016) Blockout: dynamic model selection for hierarchical deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2583\u20132591","DOI":"10.1109\/CVPR.2016.283"},{"key":"5443_CR30","doi-asserted-by":"crossref","unstructured":"Ristin M, Gall J, Guillaumin M, Gool LV (2015) From categories to subcategories: large-scale image classification with partial class label refinement. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 231\u2013239","DOI":"10.1109\/CVPR.2015.7298619"},{"key":"5443_CR31","unstructured":"Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2015) Fitnets: hints for thin deep nets. In: International conference on learning representations"},{"issue":"3","key":"5443_CR32","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"5443_CR33","doi-asserted-by":"crossref","unstructured":"Salakhutdinov R, Torralba A, Tenenbaum J (2011) Learning to share visual appearance for multiclass object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1481\u20131488","DOI":"10.1109\/CVPR.2011.5995720"},{"issue":"1","key":"5443_CR34","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s11042-014-2292-8","volume":"75","author":"K Shirahama","year":"2016","unstructured":"Shirahama K, Grzegorzek M (2016) Towards large-scale multimedia retrieval enriched by knowledge about human interpretation. Multimed Tools Appl 75(1):297\u2013331","journal-title":"Multimed Tools Appl"},{"key":"5443_CR35","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations"},{"key":"5443_CR36","unstructured":"Singh S, Hoiem D, Forsyth D (2016) Swapout: learning an ensemble of deep architectures. In: Advances in neural information processing systems, pp 28\u201336"},{"key":"5443_CR37","unstructured":"Snoek J, Rippel O, Swersky K, Kiros R, Satish N, Sundaram N, Patwary M, Mr P, Adams R (2015) Scalable bayesian optimization using deep neural networks. In: International conference on machine learning, pp 2171\u20132180"},{"key":"5443_CR38","unstructured":"Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2015) Striving for simplicity: the all convolutional net. In: International conference on learning representations workshops"},{"issue":"1","key":"5443_CR39","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"5443_CR40","unstructured":"Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks. In: International conference on learning representations workshops"},{"key":"5443_CR41","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 the IEEE Conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5443_CR42","unstructured":"Targ S, Almeida D, Lyman K (2016) Resnet in resnet: generalizing residual architectures. In: International conference on learning representations workshops"},{"key":"5443_CR43","first-page":"2579","volume":"9","author":"L Maaten van der","year":"2008","unstructured":"van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9:2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"5443_CR44","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"4","key":"5443_CR45","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2017) Show and tell: lessons learned from the 2015 mscoco image captioning challenge. IEEE Trans Pattern Anal Mach Intell 39(4):652\u2013663","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5443_CR46","unstructured":"Visin F, Kastner K, Cho K, Matteucci M, Courville A, Bengio Y (2015) Renet: a recurrent neural network based alternative to convolutional networks. arXiv: 1505.00393"},{"key":"5443_CR47","doi-asserted-by":"crossref","unstructured":"Wang J, Yang J, Kai Y, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3360\u20133367","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"5443_CR48","doi-asserted-by":"crossref","unstructured":"Wang J, Yi Y, Mao J, Huang Z, Huang C, Xu W (2016) Cnn-rnn: a unified framework for multi-label image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2285\u20132294","DOI":"10.1109\/CVPR.2016.251"},{"key":"5443_CR49","doi-asserted-by":"crossref","unstructured":"Yan Z, Zhang H, Piramuthu R, Jagadeesh V, DeCoste D, Di W, Yizhou Y (2015) Hd-cnn: hierarchical deep convolutional neural networks for large scale visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2740\u20132748","DOI":"10.1109\/ICCV.2015.314"},{"key":"5443_CR50","doi-asserted-by":"crossref","unstructured":"Yan G, Wang Y, Liao Z (2016) Lstm for image annotation with relative visual importance. In: British machine vision conference","DOI":"10.5244\/C.30.78"},{"key":"5443_CR51","unstructured":"Yang J, Kai Y, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 1794\u20131801"},{"key":"5443_CR52","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"5443_CR53","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. In: British machine vision conference","DOI":"10.5244\/C.30.87"},{"key":"5443_CR54","doi-asserted-by":"crossref","unstructured":"Zuo Z, Shuai B, Wang G, Liu X, Wang X, Wang B, Chen Y (2015) Convolutional recurrent neural networks: learning spatial dependencies for image representation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 18\u201326","DOI":"10.1109\/CVPRW.2015.7301268"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-5443-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-5443-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-5443-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T06:36:39Z","timestamp":1660113399000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-5443-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,12]]},"references-count":54,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2018,4]]}},"alternative-id":["5443"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-5443-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,12]]}}}