{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T06:38:35Z","timestamp":1773470315990,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1109\/icip.2016.7532983","type":"proceedings-article","created":{"date-parts":[[2016,8,17]],"date-time":"2016-08-17T21:22:06Z","timestamp":1471468926000},"page":"3364-3368","source":"Crossref","is-referenced-by-count":17,"title":["Beyond caption to narrative: Video captioning with multiple sentences"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Shin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsunori","family":"Ohnishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","article-title":"Wi-kicorpus: A word-sense disambiguated multilingual corpus","author":"reese","year":"2010","journal-title":"LREC"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref31","article-title":"pronoun resolution backwards","author":"angeli","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref36","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"CVPR"},{"key":"ref35","article-title":"Distributed representations of sentences and documents","author":"le","year":"2014","journal-title":"ICML"},{"key":"ref34","first-page":"313","article-title":"Building a large annotated corpus of english: The penn treebank","volume":"19","author":"marcus","year":"1993","journal-title":"Computational Linguistics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref40","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2015","journal-title":"ICLRE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1145\/2671188.2749320","article-title":"Heterogeneous semantic level features fusion for action recognition","author":"cai","year":"2015","journal-title":"ICMR"},{"key":"ref13","article-title":"A discriminative cnn video representation for event detection","author":"xu","year":"2015","journal-title":"CVPR"},{"key":"ref14","article-title":"Action recognition with trajectory-pooled deep-convolutional descriptors","author":"wang","year":"2015","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref17","article-title":"Jointly modeling embedding and translation to bridge video and language","author":"pan","year":"2016","journal-title":"CVPR"},{"key":"ref18","article-title":"Video captioning with recurrent networks based on frame- and video-level features and visual content classification","author":"shetty","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref4","article-title":"Show and tell: A neural image caption generator","author":"vinyals","year":"2015","journal-title":"CVPR"},{"key":"ref27","article-title":"Using descriptive video services to create a large data source for video annotation research","author":"torabi","year":"2015","journal-title":"arXiv 1503 01070"},{"key":"ref3","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"2015","journal-title":"CVPR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/217279.215266"},{"key":"ref29","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIP.2013.6707637"},{"key":"ref8","first-page":"674","article-title":"An iterative image registration technique with an application to stereo vision","volume":"81","author":"lucas","year":"1981","journal-title":"IJCAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref2","article-title":"From captions to visual concepts and back","author":"fang","year":"2015","journal-title":"CVPR"},{"key":"ref9","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"ECCV"},{"key":"ref1","article-title":"Mind's eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"CVPR"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref21","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014","journal-title":"ILSVRC"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref23","article-title":"A discriminative CNN video representation for event detection","author":"xu","year":"2015","journal-title":"CVPR"},{"key":"ref44","article-title":"Msr-vtt: A large video description dataset for bridging video and language","author":"xu","year":"2016","journal-title":"CVPR"},{"key":"ref26","article-title":"The lear submission at thumos 2014","author":"oneata","year":"0"},{"key":"ref43","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"ACL"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85760-0_71"}],"event":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","location":"Phoenix, AZ, USA","start":{"date-parts":[[2016,9,25]]},"end":{"date-parts":[[2016,9,28]]}},"container-title":["2016 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7527113\/7532277\/07532983.pdf?arnumber=7532983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T20:54:02Z","timestamp":1498337642000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7532983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icip.2016.7532983","relation":{},"subject":[],"published":{"date-parts":[[2016,9]]}}}