{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T12:54:00Z","timestamp":1780145640797,"version":"3.54.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"23","license":[{"start":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61622115"],"award-info":[{"award-number":["61622115"]}],"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":["61472281"],"award-info":[{"award-number":["61472281"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013285","name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning","doi-asserted-by":"crossref","award":["GZ2015005"],"award-info":[{"award-number":["GZ2015005"]}],"id":[{"id":"10.13039\/501100013285","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing","award":["17DZ2251600"],"award-info":[{"award-number":["17DZ2251600"]}]},{"name":"IBM Shared University Research Awards Program","award":["2018"],"award-info":[{"award-number":["2018"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s11042-018-6228-6","type":"journal-article","created":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T05:59:57Z","timestamp":1528178397000},"page":"31159-31175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Looking deeper and transferring attention for image captioning"],"prefix":"10.1007","volume":"77","author":[{"given":"Fang","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengjie","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,6,5]]},"reference":[{"key":"6228_CR1","unstructured":"Banerjee S, Lavie A (2005) METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proc. ACL Workshop IEEMMTS\u201905, vol 29, pp 65\u201372"},{"issue":"8","key":"6228_CR2","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915\u20131929","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6228_CR3","doi-asserted-by":"crossref","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. In: Proc. ECCV\u201910, pp 15\u201329","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"6228_CR4","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: Proc. ECCV\u201914, pp 529\u2013545","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"6228_CR5","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc. CVPR\u201916, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"6228_CR6","doi-asserted-by":"publisher","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":"6228_CR7","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":"6228_CR8","doi-asserted-by":"crossref","unstructured":"Jia X, Gavves E, Fernando B, Tuytelaars T (2015) Guiding the long-short term memory model for image caption generation. In: Proc. ICCV\u201915, pp 2407\u20132415","DOI":"10.1109\/ICCV.2015.277"},{"key":"6228_CR9","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proc. CVPR\u201915, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"6228_CR10","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proc. ECCV\u201914, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6228_CR11","doi-asserted-by":"crossref","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2017) Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proc. CVPR\u201917, pp 375\u2013383","DOI":"10.1109\/CVPR.2017.345"},{"key":"6228_CR12","unstructured":"Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2015) Deep captioning with multimodal recurrent neural networks (m-RNN). In: Proc. ICLR\u201915"},{"key":"6228_CR13","unstructured":"Papineni K, Roukos S, Ward T, Zhu W (2002) BLEU: a method for automatic evaluation of machine translation. In: Proc. ACL\u201902, pp 311\u2013318"},{"key":"6228_CR14","unstructured":"Prakash A, Hasan S, Lee K, Datla V, Qadir A, Liu J, Farri O (2016) Neural paraphrase generation with stacked residual LSTM networks. In: Proc. COLING\u201916, pp 2923\u20132934"},{"key":"6228_CR15","unstructured":"Reddy DR (1997) Speech understanding systems: a summary of results of the five-year research effort. Tech. rep., Carnegie-Mellon University. Computer Science Dept"},{"key":"6228_CR16","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proc. ICLR\u201915"},{"key":"6228_CR17","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"6228_CR18","unstructured":"Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Proc. NIPS\u201915, pp 2377\u20132385"},{"key":"6228_CR19","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Proc. NIPS\u201914, pp 3104\u20133112"},{"key":"6228_CR20","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: Proc. CVPR\u201915, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6228_CR21","doi-asserted-by":"crossref","unstructured":"Vedantam R, Zitnick CL, Parikh D (2015) CIDEr: consensus-based image description evaluation. In: Proc. CVPR\u201915, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"6228_CR22","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proc. CVPR\u201915, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"6228_CR23","doi-asserted-by":"crossref","unstructured":"Wu Q, Shen C, Liu L, Dick A, Hengel AVD (2016) What value do explicit high level concepts have in vision to language problems? In: Proc. CVPR\u201916, pp 203\u2013212","DOI":"10.1109\/CVPR.2016.29"},{"key":"6228_CR24","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: Proc. ICML\u201915, pp 2048\u2013 2057"},{"key":"6228_CR25","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Qiu Z, Mei T (2017) Boosting image captioning with attributes. In: Proc. ICCV\u201917, pp 4894\u20134902","DOI":"10.1109\/ICCV.2017.524"},{"key":"6228_CR26","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proc. CVPR\u201915, pp 2625\u20132634"},{"key":"6228_CR27","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: Proc. CVPR\u201916, pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6228-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6228-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6228-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T12:15:53Z","timestamp":1612440953000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6228-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,5]]},"references-count":27,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["6228"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6228-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,5]]},"assertion":[{"value":"6 September 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}