{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T03:48:28Z","timestamp":1771645708369,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222286","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"81-85","source":"Crossref","is-referenced-by-count":8,"title":["Video Question Answering Using Clip-Guided Visual-Text Attention"],"prefix":"10.1109","author":[{"given":"Shuhong","family":"Ye","sequence":"first","affiliation":[{"name":"University of Nottingham,School of Computer Science,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weikai","family":"Kong","sequence":"additional","affiliation":[{"name":"University of Nottingham,School of Computer Science,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglin","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Nottingham,School of Computer Science,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Ren","sequence":"additional","affiliation":[{"name":"University of Nottingham,School of Computer Science,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Electrical &amp; Electronic Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472362"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095044"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref20","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume-title":"ICML, 813\u2013824","volume":"139","author":"Bertasius"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"ref24","first-page":"26462","article-title":"Learning from inside: Self-driven siamese sampling and reasoning for video question answering","volume":"34","author":"Yu","year":"2021","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506276"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3293949"},{"key":"ref27","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT","author":"Devlin"},{"key":"ref28","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"ACL","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350969"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222286.pdf?arnumber=10222286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T17:48:11Z","timestamp":1747676891000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222286","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}