{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:50Z","timestamp":1740122870325,"version":"3.37.3"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2019,1,3]],"date-time":"2019-01-03T00:00:00Z","timestamp":1546473600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["U1509206,61472276"],"award-info":[{"award-number":["U1509206,61472276"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100006606","name":"Tianjin Natural Science Foundation","doi-asserted-by":"crossref","award":["15JCYBJC15400"],"award-info":[{"award-number":["15JCYBJC15400"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61876130"],"award-info":[{"award-number":["61876130"]}],"id":[{"id":"10.13039\/501100001809","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":[[2019,9]]},"DOI":"10.1007\/s11042-018-7118-7","type":"journal-article","created":{"date-parts":[[2019,1,3]],"date-time":"2019-01-03T11:11:31Z","timestamp":1546513891000},"page":"24321-24346","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Image captioning: from structural tetrad to translated sentences"],"prefix":"10.1007","volume":"78","author":[{"given":"Rui","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,3]]},"reference":[{"key":"7118_CR1","unstructured":"Aditya S, Yang Y, Baral C, Fermuller C, Aloimonos Y (2015) From images to sentences through scene description graphs using commonsense reasoning and knowledge. arXiv: 151103292"},{"key":"7118_CR2","doi-asserted-by":"crossref","unstructured":"Aneja J, Deshpande A (2018) Convolutional image captioning. In: CVPR","DOI":"10.1109\/CVPR.2018.00583"},{"key":"7118_CR3","unstructured":"Baldridge J (2005) The opennlp project. http:\/\/opennlpapacheorg\/indexhtml . Accessed 2 Feb 2012"},{"key":"7118_CR4","unstructured":"Banerjee S, Lavie A (2005) Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization"},{"key":"7118_CR5","doi-asserted-by":"crossref","unstructured":"Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua TS (2017) Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR","DOI":"10.1109\/CVPR.2017.667"},{"issue":"99","key":"7118_CR6","first-page":"1","volume":"PP","author":"G Cheng","year":"2017","unstructured":"Cheng G, Zhou P, Han J (2017) Duplex metric learning for image set classification. IEEE Trans Image Process PP(99):1\u20131","journal-title":"IEEE Trans Image Process"},{"issue":"5","key":"7118_CR7","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.1109\/TGRS.2017.2783902","volume":"56","author":"G Cheng","year":"2018","unstructured":"Cheng G, Yang C, Yao X, Guo L, Han J (2018) When deep learning meets metric learning: remote sensing image scene classification via learning discriminative cnns. IEEE Trans Geoscience Remote Sens 56(5):2811\u20132821","journal-title":"IEEE Trans Geoscience Remote Sens"},{"key":"7118_CR8","doi-asserted-by":"crossref","unstructured":"Cho K, van Merri\u00ebnboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: encoder\u2013decoder approaches. Syntax, Semantics and Structure in Statistical Translation","DOI":"10.3115\/v1\/W14-4012"},{"key":"7118_CR9","doi-asserted-by":"crossref","unstructured":"Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using rnn encoder\u2013decoder for statistical machine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics","DOI":"10.3115\/v1\/D14-1179"},{"issue":"11","key":"7118_CR10","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"Cho K, Courville A, Bengio Y (2015) Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans Multimedia 17(11):1875\u20131886","journal-title":"IEEE Trans Multimedia"},{"key":"7118_CR11","doi-asserted-by":"publisher","unstructured":"Cui H, Zhu L, Cui C, Nie X, Zhang H (2018) Efficient weakly-supervised discrete hashing for large-scale social image retrieval. Pattern Recognition Letters. https:\/\/doi.org\/10.1016\/j.patrec.2018.08.033","DOI":"10.1016\/j.patrec.2018.08.033"},{"key":"7118_CR12","doi-asserted-by":"crossref","unstructured":"Devlin J, Cheng H, Fang H, Gupta S, Deng L, He X, Zweig G, Mitchell M (2015) Language models for image captioning: the quirks and what works. arXiv: 150501809","DOI":"10.3115\/v1\/P15-2017"},{"key":"7118_CR13","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: CVPR","DOI":"10.21236\/ADA623249"},{"key":"7118_CR14","doi-asserted-by":"crossref","unstructured":"Fang H, Gupta S, Iandola F, Srivastava R K, Deng L, Doll\u00e1r P, Gao J, He X, Mitchell M, Platt J C et al (2015) From captions to visual concepts and back. In: CVPR","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"7118_CR15","doi-asserted-by":"crossref","unstructured":"Farhadi A, Endres I, Hoiem D, Forsyth D (2009) Describing objects by their attributes. In: CVPR","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"7118_CR16","doi-asserted-by":"crossref","unstructured":"Farhadi A, Hejrati M, Sadeghi M, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. In: Computer Vision\u2013ECCV","DOI":"10.1007\/978-3-642-15561-1_2"},{"issue":"8","key":"7118_CR17","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to roc analysis. Pattern Recognit Lett 27(8):861\u2013874","journal-title":"Pattern Recognit Lett"},{"key":"7118_CR18","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Hodosh M, Hockenmaier J, Lazebnik S (2014) Improving image-sentence embeddings using large weakly annotated photo collections. In: Computer Vision\u2013ECCV 2014, Springer","DOI":"10.1007\/978-3-319-10593-2_35"},{"issue":"3","key":"7118_CR19","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/TCSVT.2014.2358011","volume":"25","author":"JM Guo","year":"2015","unstructured":"Guo J M, Prasetyo H, Chen JH (2015) Content-based image retrieval using error diffusion block truncation coding features. IEEE Trans Circuits Syst Video Technol 25 (3):466\u2013481","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"1","key":"7118_CR20","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han J, Zhang D, Cheng G, Liu N, Xu D (2018) Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Sign Process Mag 35(1):84\u2013100","journal-title":"IEEE Sign Process Mag"},{"key":"7118_CR21","doi-asserted-by":"crossref","unstructured":"Han Y, Li G (2015) Describing images with hierarchical concepts and object class localization. In: Proceedings of the 5th ACM on international conference on multimedia retrieval. ACM","DOI":"10.1145\/2671188.2749290"},{"key":"7118_CR22","doi-asserted-by":"crossref","unstructured":"Hendricks LA, Venugopalan S, Rohrbach M, Mooney R, Saenko K, Darrell T (2015) Deep compositional captioning: Describing novel object categories without paired training data. In: CVPR. IEEE","DOI":"10.1109\/CVPR.2016.8"},{"key":"7118_CR23","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Intell Res 47:853\u2013899","journal-title":"J Artif Intell Res"},{"key":"7118_CR24","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. ACM","DOI":"10.1145\/2647868.2654889"},{"key":"7118_CR25","doi-asserted-by":"publisher","unstructured":"Jing P, Su Y, Nie L, Gu H, Liu J, Wang M (2018) A framework of joint low-rank and sparse regression for image memorability prediction. IEEE Transactions on Circuits and Systems for Video Technology. https:\/\/doi.org\/10.1109\/TCSVT.2018.2832095","DOI":"10.1109\/TCSVT.2018.2832095"},{"key":"7118_CR26","doi-asserted-by":"crossref","unstructured":"Johnson J, Krishna R, Stark M, Li LJ, Shamma DA, Bernstein MS, Fei-Fei L (2015) Image retrieval using scene graphs. In: CVPR. IEEE","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"7118_CR27","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: CVPR","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"7118_CR28","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. In: Proceedings of the 31st international conference on machine learning (ICML-14)"},{"key":"7118_CR29","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems"},{"key":"7118_CR30","doi-asserted-by":"crossref","unstructured":"Kulkarni G, Premraj V, Dhar S, Li S, Choi Y, Berg A C, Berg T L (2011) Baby talk: Understanding and generating simple image descriptions. In: CVPR","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"7118_CR31","doi-asserted-by":"crossref","unstructured":"Lampert CH, Nickisch H, Harmeling S (2009) Learning to detect unseen object classes by between-class attribute transfer. In: CVPR","DOI":"10.1109\/CVPR.2009.5206594"},{"issue":"Part 3","key":"7118_CR32","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1016\/j.neucom.2015.06.041","volume":"173","author":"J Li","year":"2016","unstructured":"Li J, Wu Y, Zhao J, Lu K (2016) Multi-manifold sparse graph embedding for multi-modal image classification. Neurocomputing 173(Part 3):501\u2013510","journal-title":"Neurocomputing"},{"issue":"11","key":"7118_CR33","doi-asserted-by":"publisher","first-page":"3516","DOI":"10.1109\/TCYB.2016.2565898","volume":"47","author":"J Li","year":"2016","unstructured":"Li J, Yue W, Zhao J, Ke L (2016) Low-rank discriminant embedding for multiview learning. IEEE Trans Cybern 47(11):3516\u20133529","journal-title":"IEEE Trans Cybern"},{"key":"7118_CR34","unstructured":"Li J, Zhao J, Lu K (2016) Joint feature selection and structure preservation for domain adaptation. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence. AAAI Press"},{"key":"7118_CR35","doi-asserted-by":"crossref","unstructured":"Lin CY, Och FJ (2004) Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Proceedings of the 42nd annual meeting on association for computational linguistics, association for computational linguistics","DOI":"10.3115\/1218955.1219032"},{"key":"7118_CR36","doi-asserted-by":"crossref","unstructured":"Lin T Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7118_CR37","doi-asserted-by":"publisher","unstructured":"Liu X, Xu Q, Chau T, Mu Y, Zhu L, Yan S (2018) Revisiting jump-diffusion process for visual tracking: a reinforcement learning approach. IEEE Transactions on Circuits and Systems for Video Technology. https:\/\/doi.org\/10.1109\/TCSVT.2018.2862891","DOI":"10.1109\/TCSVT.2018.2862891"},{"issue":"10","key":"7118_CR38","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1109\/TCSVT.2017.2781738","volume":"28","author":"X Liu","year":"2018","unstructured":"Liu X, Xu Y, Zhu L, Mu Y (2018) A stochastic attribute grammar for robust cross-view human tracking. IEEE Trans Circuits Syst Video Technol 28(10):2884\u20132895","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7118_CR39","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.sigpro.2018.09.007","volume":"154","author":"X Lu","year":"2019","unstructured":"Lu X, Zhu L, Cheng Z, Song X, Zhang H (2019) Efficient discrete latent semantic hashing for scalable cross-modal retrieval. Signal Process 154:217\u2013231. https:\/\/doi.org\/10.1016\/j.sigpro.2018.09.007","journal-title":"Signal Process"},{"issue":"4","key":"7118_CR40","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1109\/TMM.2012.2187179","volume":"14","author":"Z Ma","year":"2012","unstructured":"Ma Z, Nie F, Yang Y, Uijlings JR, Sebe N (2012) Web image annotation via subspace-sparsity collaborated feature selection. IEEE Trans Multimedia 14(4):1021\u20131030","journal-title":"IEEE Trans Multimedia"},{"key":"7118_CR41","doi-asserted-by":"crossref","unstructured":"Ma Z, Yang Y, Cai Y, Sebe N, Hauptmann AG (2012) Knowledge adaptation for ad hoc multimedia event detection with few exemplars. In: Proceedings of the 20th ACM international conference on multimedia. ACM","DOI":"10.1145\/2393347.2393414"},{"key":"7118_CR42","unstructured":"Mao J, Xu W, Yang Y, Wang J, Yuille AL (2014) Explain images with multimodal recurrent neural networks. NIPS Deep Learning Workshop"},{"issue":"7","key":"7118_CR43","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1109\/TCSVT.2014.2372371","volume":"25","author":"ML Mekhalfi","year":"2015","unstructured":"Mekhalfi ML, Melgani F, Bazi Y, Alajlan N (2015) A compressive sensing approach to describe indoor scenes for blind people. IEEE Trans Circuits Syst Video Technol 25(7):1246\u20131257","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7118_CR44","unstructured":"Mitchell M, Han X, Dodge J, Mensch A, Goyal A, Berg A, Yamaguchi K, Berg T, Stratos K, Daum\u00e9 H III (2012) Midge: generating image descriptions from computer vision detections. In: Proceedings of the 13th conference of the European chapter of the association for computational linguistics, association for computational linguistics"},{"issue":"3","key":"7118_CR45","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1109\/TCSVT.2014.2351092","volume":"25","author":"JS Pan","year":"2015","unstructured":"Pan JS, Feng Q, Yan L, Yang JF (2015) Neighborhood feature line segment for image classification. IEEE Trans Circuits Syst Video Technol 25(3):387\u2013398","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7118_CR46","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, association for computational linguistics","DOI":"10.3115\/1073083.1073135"},{"key":"7118_CR47","doi-asserted-by":"crossref","unstructured":"Parikh D, Grauman K (2011) Relative attributes. In: 2011 international conference on computer vision. IEEE","DOI":"10.1109\/ICCV.2011.6126281"},{"issue":"5","key":"7118_CR48","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TCSVT.2013.2280096","volume":"24","author":"Z Ren","year":"2014","unstructured":"Ren Z, Gao S, Chia LT, Tsang IWH (2014) Region-based saliency detection and its application in object recognition. IEEE Trans Circuits Syst Video Technol 24 (5):769\u2013779","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7118_CR49","doi-asserted-by":"crossref","unstructured":"Rohrbach A, Rohrbach M, Schiele B (2015) The long-short story of movie description. In: Pattern recognition. Springer","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"7118_CR50","doi-asserted-by":"crossref","unstructured":"Schuster S, Krishna R, Chang A, Fei-Fei L, Manning CD (2015) Generating semantically precise scene graphs from textual descriptions for improved image retrieval. In: Proceedings of the fourth workshop on vision and language","DOI":"10.18653\/v1\/W15-2812"},{"key":"7118_CR51","doi-asserted-by":"crossref","unstructured":"Socher R, Karpathy A, Le QV, Manning CD, Ng AY (2014) Grounded compositional semantics for finding and describing images with sentences. Trans Assoc Comput Linguist 2(1):207\u2013218","DOI":"10.1162\/tacl_a_00177"},{"key":"7118_CR52","doi-asserted-by":"crossref","unstructured":"Song X, Shi Y, Chen X, Han Y (2018) Explore multi-step reasoning in video question answering. In: Proceedings of the ACM international conference on multimedia (ACM MM)","DOI":"10.1145\/3240508.3240563"},{"key":"7118_CR53","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems"},{"key":"7118_CR54","unstructured":"Thomason J, Venugopalan S, Guadarrama S, Saenko K, Mooney R (2014) Integrating language and vision to generate natural language descriptions of videos in the wild. In: Proceedings of the 25th international conference on computational Linguistics (COLING) August"},{"key":"7118_CR55","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: CVPR","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"7118_CR56","doi-asserted-by":"crossref","unstructured":"Wang C, Yan S, Zhang L, Zhang HJ (2009) Multi-label sparse coding for automatic image annotation. In: CVPR. IEEE","DOI":"10.1109\/CVPR.2009.5206866"},{"issue":"12","key":"7118_CR57","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.1109\/TCSVT.2015.2477939","volume":"25","author":"H Wang","year":"2015","unstructured":"Wang H, Xiao B, Wang L, Zhu F, Jiang YG, Wu J (2015) Chcf: a cloud-based heterogeneous computing framework for large-scale image retrieval. IEEE Trans Circuits Syst Video Technol 25(12):1900\u20131913","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7118_CR58","doi-asserted-by":"crossref","unstructured":"Wang B, Xu Y, Han Y, Hong R (2018) Movie question answering: remembering the textual cues for layered visual contents. In: AAAI","DOI":"10.1609\/aaai.v32i1.12253"},{"key":"7118_CR59","doi-asserted-by":"crossref","unstructured":"Wang H, Xu Y, Han Y (2018) Spotting and aggregating salient regions for video captioning. In: Proceedings of the ACM international conference on multimedia (ACM MM)","DOI":"10.1145\/3240508.3240677"},{"key":"7118_CR60","doi-asserted-by":"crossref","unstructured":"Werbos PJ (1990) Backpropagation through time: what it does and how to do it. In: Proceedings of the IEEE","DOI":"10.1109\/5.58337"},{"key":"7118_CR61","doi-asserted-by":"crossref","unstructured":"Wu A, Han Y (2018) Multi-modal circulant fusion for video-to-language and backward. In: IJCAI, pp 1029\u20131035","DOI":"10.24963\/ijcai.2018\/143"},{"key":"7118_CR62","doi-asserted-by":"crossref","unstructured":"Wu Q, Shen C, Liu L, Dick A, van den Hengel A (2016) What value do explicit high level concepts have in vision to language problems? In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.29"},{"issue":"10","key":"7118_CR63","doi-asserted-by":"publisher","first-page":"4933","DOI":"10.1109\/TIP.2018.2846664","volume":"27","author":"Y Xu","year":"2018","unstructured":"Xu Y, Han Y, Hong R, Tian Q (2018) Sequential video vlad: training the aggregation locally and temporally. IEEE Trans Image Process 27(10):4933\u20134944","journal-title":"IEEE Trans Image Process"},{"key":"7118_CR64","unstructured":"Yang Y, Shen HT, Ma Z, Huang Z, Zhou X (2011) l2, 1-norm regularized discriminative feature selection for unsupervised learning. In: IJCAI proceedings-international joint conference on artificial intelligence. Citeseer"},{"key":"7118_CR65","unstructured":"Yang Y, Teo CL, Daum\u00e9 H III, Aloimonos Y (2011) Corpus-guided sentence generation of natural images. In: Proceedings of the conference on empirical methods in natural language processing, association for computational linguistics"},{"key":"7118_CR66","doi-asserted-by":"crossref","unstructured":"Yang Z, Han Y, Wang Z (2017) Catching the temporal regions-of-interest for video captioning. In: Proceedings of the ACM international conference on multimedia (ACM MM)","DOI":"10.1145\/3123266.3123327"},{"key":"7118_CR67","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2:67\u201378","journal-title":"Trans Assoc Comput Linguist"},{"issue":"2","key":"7118_CR68","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TCSVT.2013.2276172","volume":"24","author":"L Zhang","year":"2014","unstructured":"Zhang L, Wang L, Lin W, Yan S (2014) Geometric optimum experimental design for collaborative image retrieval. IEEE Trans Circuits Syst Video Technol 24(2):346\u2013359","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"8","key":"7118_CR69","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1109\/TCSVT.2017.2682196","volume":"28","author":"S Zhao","year":"2018","unstructured":"Zhao S, Liu Y, Han Y, Hong R, Hu Q, Tian Q (2018) Pooling the convolutional layers in deep convnets for video action recognition. IEEE Trans Circuits Syst Video Technol 28(8):1839\u20131849","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7118_CR70","doi-asserted-by":"crossref","unstructured":"Zhou D, Huang J, Sch\u00f6lkopf B (2006) Learning with hypergraphs: clustering, classification and embedding. In: Advances in neural information processing systems","DOI":"10.7551\/mitpress\/7503.003.0205"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-7118-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-7118-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-7118-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T17:07:16Z","timestamp":1694538436000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-7118-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,3]]},"references-count":70,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["7118"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-7118-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2019,1,3]]},"assertion":[{"value":"26 June 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}