{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:19:46Z","timestamp":1775261986299,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030033378","type":"print"},{"value":"9783030033385","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-03338-5_2","type":"book-chapter","created":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T23:57:42Z","timestamp":1541116662000},"page":"15-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Accurate Guidance for Image Caption Generation"],"prefix":"10.1007","author":[{"given":"Xinyuan","family":"Qi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,3]]},"reference":[{"key":"2_CR1","unstructured":"Kulkarni, G., et al.: BabyTalk: understanding and generating simple image descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1601\u20131608. IEEE Computer Society (2011)"},{"issue":"4","key":"2_CR2","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2015","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677\u2013691 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Jia, X., et al.: Guiding the long-short term memory model for image caption generation. In: IEEE International Conference on Computer Vision, pp. 2407\u20132415. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.277"},{"key":"2_CR4","unstructured":"Bahdanau, D., et al.: Neural machine translation by jointly learning to align and translate. Comput. Sci. (2014)"},{"issue":"8","key":"2_CR5","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., et al.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"You, Q., et al.: Image Captioning with Semantic Attention. In: IEEE Computer Vision and Pattern Recognition, pp. 4651\u20134659. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"2_CR7","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. Comput. Sci. 2048\u20132057 (2015)"},{"key":"2_CR8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179","volume-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"K Cho","year":"2014","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. Comput, Sci (2014)"},{"key":"2_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., et al.: 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":"2_CR10","doi-asserted-by":"crossref","unstructured":"Karpathy, A., et.al.: Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Ross, G., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Computer Vision and Pattern Recognition, pp. 580\u2013587. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440\u20131448. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"2_CR13","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep Residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR15","unstructured":"Simonyan, K., et al.: Very deep convolutional networks for large-scale image recognition. Comput. Sci. (2014)"},{"issue":"4","key":"2_CR16","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677\u2013691 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR17","unstructured":"Mao, J., et al.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint arXiv:1412.6632 (2014)"},{"issue":"12","key":"2_CR18","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TPAMI.2016.2642953","volume":"39","author":"K Fu","year":"2015","unstructured":"Fu, K., et al.: Aligning where to see and what to tell: image captioning with region-based attention and scene-specific contexts. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2321\u20132334 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-319-71589-6_10","volume-title":"Image and Graphics","author":"Z Yang","year":"2017","unstructured":"Yang, Z., Zhang, Y.-J., Rehman, S., Huang, Y.: Image captioning with object detection and localization. In: Zhao, Y., Kong, X., Taubman, D. (eds.) ICIG 2017. LNCS, vol. 10667, pp. 109\u2013118. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71589-6_10"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., et al.: Self-critical sequence training for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1179\u20131195. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.131"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03338-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T23:05:36Z","timestamp":1775257536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03338-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030033378","9783030033385"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03338-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"3 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prcv.qyhw.net.cn\/?lang=en&meeting_id=255","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"}]}}