{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T20:24:02Z","timestamp":1729628642366,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268968","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"430-436","source":"Crossref","is-referenced-by-count":11,"title":["Early and late integration of audio features for automatic video description"],"prefix":"10.1109","author":[{"given":"Chiori","family":"Hori","sequence":"first","affiliation":[]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[]},{"given":"Tim K.","family":"Marks","sequence":"additional","affiliation":[]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"iv","article-title":"Consensus network decoding for statistical machine translation system combination","volume":"4","author":"chai sim","year":"2007","journal-title":"Acoustics Speech and Signal Processing 2007 ICASSP 2007 IEEE International Conference on"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"163","DOI":"10.21437\/Eurospeech.1997-68","article-title":"Ex-plicit word error minimization in n-best list rescoring","volume":"97","author":"stolcke","year":"1997","journal-title":"Eurospeech"},{"key":"ref12","article-title":"Minimum bayes-risk decoding for statistical machine translation","author":"kumar","year":"2004","journal-title":"Tech Rep JOHNS HOPKINS UNIV BALTIMORE MD CENTER FOR LAN-GUAGE AND SPEECH PROCESSING (CLSP)"},{"key":"ref13","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 of the Association for Computational Linguistics July 6–12 2002 Philadelphia PA USA"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref17","first-page":"1097","article-title":"Im-agenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","volume":"abs 1409 473","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","author":"k chorowski","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref6","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref5","article-title":"Network in network","volume":"abs 1312 4400","author":"lin","year":"2013","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref2","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref9","first-page":"78","article-title":"Posterior probability decoding, confidence estimation and system combination","volume":"27","author":"evermann","year":"2000","journal-title":"Proc Speech Transcription Workshop"},{"key":"ref20","article-title":"Jointly modeling embedding and translation to bridge video and language","volume":"abs 1505 1861","author":"pan","year":"2015","journal-title":"CoRR"},{"key":"ref22","article-title":"Microsoft COCO captions: Data collection and evaluation server","volume":"abs 1504 325","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref21","article-title":"Video paragraph captioning using hierarchical recurrent neural networks","volume":"abs 1510 7712","author":"yu","year":"2015","journal-title":"CoRR"},{"key":"ref24","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":"ref23","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 Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2017,12,16]]},"location":"Okinawa, Japan","end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08268968.pdf?arnumber=8268968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T06:17:01Z","timestamp":1660371421000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268968","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}