{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:07:20Z","timestamp":1777651640202,"version":"3.51.4"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053476","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"2423-2427","source":"Crossref","is-referenced-by-count":9,"title":["Video Question Generation via Semantic Rich Cross-Modal Self-Attention Networks Learning"],"prefix":"10.1109","author":[{"given":"Yu-Siang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Ting","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-Hsi","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe-Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Winston H.","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref14","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref4","article-title":"Embodied Question Answering","author":"das","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1123"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref2","article-title":"From film to video: Multi-turn question answering with multi-modal context","volume":"abs 1812 7023","author":"nguyen","year":"2018","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref1","article-title":"Lifelong learning for image captioning by asking natural language questions","author":"shen","year":"2019","journal-title":"ICCV"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053476.pdf?arnumber=9053476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:25:22Z","timestamp":1656375922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053476","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}