{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T03:38:04Z","timestamp":1776310684743,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"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":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897613","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T17:27:24Z","timestamp":1667496444000},"page":"3903-3907","source":"Crossref","is-referenced-by-count":1,"title":["Video-Grounded Dialogues with Joint Video and Image Training"],"prefix":"10.1109","author":[{"given":"Hangyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,College of Information Science & Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingming","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science & Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Binghamton University,Department of Computer Science,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682583"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065823"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref15","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref17","article-title":"Dialog system technology challenge 7","author":"Yoshino","year":"2019"},{"key":"ref18","article-title":"The eighth dialog system technology challenge","author":"Kim","year":"2019"},{"key":"ref19","article-title":"Multi-step joint-modality attention network for scene-aware dialogue system","author":"Chu","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16273"},{"key":"ref21","article-title":"Learning reasoning paths over semantic graphs for video-grounded dialogues","author":"Le","year":"2021"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","location":"Bordeaux, France","start":{"date-parts":[[2022,10,16]]},"end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897613.pdf?arnumber=9897613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:22:54Z","timestamp":1773778974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897613","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}