{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:17:55Z","timestamp":1787012275737,"version":"3.56.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/iccv.2017.450","type":"proceedings-article","created":{"date-parts":[[2017,12,25]],"date-time":"2017-12-25T16:51:45Z","timestamp":1514220705000},"page":"4203-4212","source":"Crossref","is-referenced-by-count":271,"title":["Attention-Based Multimodal Fusion for Video Description"],"prefix":"10.1109","author":[{"given":"Chiori","family":"Hori","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teng-Yok","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bret","family":"Harsham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim K.","family":"Marks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhiko","family":"Sumi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ICML 2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref36","article-title":"ADADELTA: an adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"CoRR"},{"key":"ref35","article-title":"Video paragraph captioning using hierarchical recurrent neural networks","author":"yu","year":"2015","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5_25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552966"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-380"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref17","first-page":"1097","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref18","article-title":"Network in network","author":"lin","year":"2013","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4640"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref3","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref6","first-page":"577","author":"chorowski","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref8","first-page":"1","article-title":"Maximum entropy and mce based hmm stream weight estimation for audio-visual asr","volume":"1","author":"gravier","year":"2002","journal-title":"Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref2","first-page":"4945","author":"bahdanau","year":"2016","journal-title":"End-to-end attention-based large vocabulary speech recognition"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref20","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2014","journal-title":"CoRR"},{"key":"ref22","article-title":"Jointly modeling embedding and translation to bridge video and language","author":"pan","year":"2015","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007468413059"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref23","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02"},{"key":"ref26","article-title":"Chainer: a next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref25","article-title":"Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"}],"event":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","location":"Venice","start":{"date-parts":[[2017,10,22]]},"end":{"date-parts":[[2017,10,29]]}},"container-title":["2017 IEEE International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8234942\/8237262\/08237712.pdf?arnumber=8237712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,5]],"date-time":"2018-02-05T17:34:46Z","timestamp":1517852086000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/ieeexplore.ieee.org\/document\/8237712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":36,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/iccv.2017.450","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}