{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:40:17Z","timestamp":1770349217219,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682583","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"2352-2356","source":"Crossref","is-referenced-by-count":48,"title":["End-to-end Audio Visual Scene-aware Dialog Using Multimodal Attention-based Video Features"],"prefix":"10.1109","author":[{"given":"Chiori","family":"Hori","sequence":"first","affiliation":[]},{"given":"Huda","family":"Alamri","sequence":"additional","affiliation":[]},{"given":"Jue","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[]},{"given":"Anoop","family":"Cherian","sequence":"additional","affiliation":[]},{"given":"Tim K.","family":"Marks","sequence":"additional","affiliation":[]},{"given":"Vincent","family":"Cartillier","sequence":"additional","affiliation":[]},{"given":"Raphael Gontijo","family":"Lopes","sequence":"additional","affiliation":[]},{"given":"Abhishek","family":"Das","sequence":"additional","affiliation":[]},{"given":"Irfan","family":"Essa","sequence":"additional","affiliation":[]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Audio Visual Scene-aware dialog (AVSD) Track for Natural Language Generation in DSTC7","author":"alamri","year":"2019","journal-title":"DSTC7 workshop at AAAI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref12","article-title":"Audio visual scene-aware dialog (avsd) challenge at dstc7","author":"alamri","year":"2018","journal-title":"arXiv preprint arXiv 1806 00525"},{"key":"ref13","article-title":"Video paragraph captioning using hierarchical recurrent neural networks","volume":"abs 1510 7712","author":"yu","year":"2015","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268968"},{"key":"ref17","article-title":"Sound-net: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref7","article-title":"Visual dialog","volume":"abs 1611 8669","author":"das","year":"2016","journal-title":"CoRR"},{"key":"ref2","article-title":"Overview of the sixth dialog system technology challenge: DSTC6","author":"hori","year":"2018","journal-title":"Computer Speech and Language"},{"key":"ref1","article-title":"A neural conversational model","author":"vinyals","year":"2015","journal-title":"arXiv preprint arXiv 1506 01051"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref22","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682583.pdf?arnumber=8682583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:04Z","timestamp":1657854604000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682583","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}