{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:54:19Z","timestamp":1764842059496,"version":"3.37.3"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:00:00Z","timestamp":1519689600000},"content-version":"tdm","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":["61673402","61273270"],"award-info":[{"award-number":["61673402","61273270"]}],"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":["60802069"],"award-info":[{"award-number":["60802069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1007\/s11063-018-9807-7","type":"journal-article","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:46:45Z","timestamp":1519692405000},"page":"177-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Image Captioning with Text-Based Visual Attention"],"prefix":"10.1007","volume":"49","author":[{"given":"Chen","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,27]]},"reference":[{"key":"9807_CR1","unstructured":"Kiros R, Salakhutdinov R, Zemel R S (2014) Multimodal neural language models. In: ICML"},{"key":"9807_CR2","unstructured":"Mao J, Xu W, Yang Y, Wang J et al. (2015) Deep captioning with Multimodal recurrent neural networks (M-RNN). In: ICLR"},{"key":"9807_CR3","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":"9807_CR4","unstructured":"Xu K, Ba JL, Kiros R et al (2016) Show, attend and tell: neural image caption generation with visual attention. arXiv:1502.03044v3 [cs.LG]"},{"key":"9807_CR5","unstructured":"Dzmitry B, Kyunghyun C, Yoshua B (2014) Neural machine translation by jointly learning to align and translate. arXiv:409.0473"},{"key":"9807_CR6","doi-asserted-by":"crossref","unstructured":"Zhou L, Xu C, Koch P, Corso JJ (2016) Watch what you just said: image captioning with text-conditional attention. arXiv:1606.04621 [cs.CV]","DOI":"10.1145\/3126686.3126717"},{"key":"9807_CR7","doi-asserted-by":"crossref","unstructured":"LeCun YA, Bottou L, Orr GB, M\u00fcller KR (2012) Efficient backprop. In: Montavon G, Orr GB, M\u00fcller KR (eds) Neural networks: tricks of the trade. Lecture Notes in Computer Science, vol 7700. Springer, Berlin, Heidelberg, pp 9\u201348.","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"9807_CR8","doi-asserted-by":"crossref","unstructured":"Mao J, Wei X, Yang Y, Wang J, Huang Z, Yuille A (2015) Learning like a child: fast novel visual concept learning from sentence descriptions of images. arXiv:1504.06692 [cs.CV]","DOI":"10.1109\/ICCV.2015.291"},{"key":"9807_CR9","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs.CV]"},{"key":"9807_CR10","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft coco: common objects in context. arXiv preprint arXiv:1405.0312"},{"key":"9807_CR11","unstructured":"Papineni K, Roukos S, Ward T, Zhu W (2002) BLEU: a method for automatic evaluation of machine translation. In: ACL, pp 311\u2013318"},{"key":"9807_CR12","unstructured":"Chen X, Fang H, Lin TY, Vedantam et al (2015) Microsoft coco captions: data collection and evaluation server. arXiv:1504.00325"},{"key":"9807_CR13","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision. arXiv:1512.00567"},{"key":"9807_CR14","doi-asserted-by":"crossref","unstructured":"Jia X, Gavves E, Fernando B et al (2015) Guiding the long-short term memory model for image caption generation. In: ICCV","DOI":"10.1109\/ICCV.2015.277"},{"key":"9807_CR15","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: CVPR","DOI":"10.1109\/CVPR.2016.503"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11063-018-9807-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-018-9807-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-018-9807-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T18:32:42Z","timestamp":1570818762000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11063-018-9807-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,27]]},"references-count":15,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["9807"],"URL":"https:\/\/doi.org\/10.1007\/s11063-018-9807-7","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2018,2,27]]},"assertion":[{"value":"27 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}