{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:07:46Z","timestamp":1760710066672,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030368012"},{"type":"electronic","value":"9783030368029"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-36802-9_10","type":"book-chapter","created":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T18:03:03Z","timestamp":1575568983000},"page":"83-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Dense Image Captioning Based on Precise Feature Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2408-366X","authenticated-orcid":false,"given":"Zhiqiang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yunye","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Shi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6093-5516","authenticated-orcid":false,"given":"Wenxin","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Li","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Gang","family":"He","sequence":"additional","affiliation":[]},{"given":"Yibo","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Zhuo","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,5]]},"reference":[{"key":"10_CR1","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Explain Images with Multimodal Recurrent Neural Networks. arXiv:1410.1090 (2014)"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"10_CR3","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Computer Vision, pp. 2048\u20132057 (2015)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., Hengel, A.: What value do explicit high level concepts have in vision to language problem? In: Computer Vision and Pattern Recognition, pp. 203\u2013212 (2016)","DOI":"10.1109\/CVPR.2016.29"},{"issue":"8","key":"10_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., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, R., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Computer Vision and Pattern Recognition, pp. 1179\u20131195 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: Computer Vision and Pattern Recognition, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"10_CR8","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Yang, L., Tang, K.D., Yang, J., Li, L.: Dense captioning with joint inference and visual context. In: Computer Vision and Pattern Recognition, pp. 1978\u20131987 (2017)","DOI":"10.1109\/CVPR.2017.214"},{"key":"10_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representation (2015)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: mask R-CNN. In: International Conference on Computer Vision, pp. 2908\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"1","key":"10_CR12","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"10_CR13","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop, pp. 65\u201372 (2005)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36802-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:48:56Z","timestamp":1710262136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-36802-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030368012","9783030368029"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36802-9_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"5 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ajiips.com.au\/iconip2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}