{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:56:04Z","timestamp":1742957764995,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811072987"},{"type":"electronic","value":"9789811072994"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-981-10-7299-4_21","type":"book-chapter","created":{"date-parts":[[2017,11,29]],"date-time":"2017-11-29T16:27:13Z","timestamp":1511972833000},"page":"258-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Relevance and Coherence Based Image Caption"],"prefix":"10.1007","author":[{"given":"Tao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,11,30]]},"reference":[{"key":"21_CR1","unstructured":"Satanjeev, B., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments, pp. 228\u2013231 (2005)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Lawrence Zitnick, C.: Mind\u2019s eye: a recurrent visual representation for image caption generation, pp. 2422\u20132431 (2015)","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., Saenko, K.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625\u20132634 (2015)","DOI":"10.21236\/ADA623249"},{"key":"21_CR4","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.: From captions to visual concepts and back. In: CVPR, pp. 1473\u20131482 (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"21_CR5","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. JAIR 47, 853\u2013899 (2013)","journal-title":"JAIR"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"21_CR7","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"21_CR8","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal neural language models. In: ICML, pp. 595\u2013603 (2014)"},{"key":"21_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. arXiv preprint arXiv:1612.01887 (2016)","DOI":"10.1109\/CVPR.2017.345"},{"key":"21_CR11","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint arXiv:1412.6632 (2014)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: CVPR, pp. 4594\u20134602 (2016)","DOI":"10.1109\/CVPR.2016.497"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"21_CR14","unstructured":"Ranzato, M.A., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. arXiv preprint arXiv:1612.00563 (2016)","DOI":"10.1109\/CVPR.2017.131"},{"key":"21_CR16","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)"},{"key":"21_CR17","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Tran, K., He, X., Zhang, L., Sun, J., Carapcea, C., Thrasher, C., Buehler, C., Sienkiewicz, C.: Rich image captioning in the wild. In: CVPR, pp. 49\u201356 (2016)","DOI":"10.1109\/CVPRW.2016.61"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"3\u20134","key":"21_CR20","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"21_CR21","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. arXiv preprint arXiv:1611.01646 (2016)","DOI":"10.1109\/ICCV.2017.524"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"21_CR24","first-page":"67","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. ACL 2, 67\u201378 (2014)","journal-title":"ACL"}],"container-title":["Communications in Computer and Information Science","Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-7299-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T14:13:33Z","timestamp":1709820813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-10-7299-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9789811072987","9789811072994"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-7299-4_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"30 November 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Chinese Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cccv2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ccf-cccv.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}