{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:34:34Z","timestamp":1783712074655,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011639"],"award-info":[{"award-number":["2023A1515011639"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Instrum. Meas."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tim.2025.3571119","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T17:56:36Z","timestamp":1747677396000},"page":"1-14","source":"Crossref","is-referenced-by-count":3,"title":["Semantic Distance-Aware Cross-Modal Attention Mechanism for Video Question Answering"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3630-5821","authenticated-orcid":false,"given":"Mingyang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0400-9366","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-4412","authenticated-orcid":false,"given":"Ruomei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0031-7721","authenticated-orcid":false,"given":"Baoquan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-9988","authenticated-orcid":false,"given":"Fuwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00117"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3342222"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3256459"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3470246"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3353830"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413868"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105280"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref14","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref17","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lei"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3264524"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3534219"},{"key":"ref21","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. NIPS","author":"Lu"},{"key":"ref22","first-page":"2920","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Veli\u010dkovi\u0107"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/139"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093596"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3372210"},{"key":"ref33","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref37","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* Chatgpt Quality","author":"Chiang","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612239"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3224539"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3552465"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3199247"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/178"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3358726"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3414-05.2005"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00172"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref59","first-page":"26462","article-title":"Learning from inside: Self-driven Siamese sampling and reasoning for video question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref62","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3333192"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref70","article-title":"VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners","author":"Yan","year":"2022","journal-title":"arXiv:2212.04979"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Instrumentation and Measurement"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/19\/10764799\/11007207.pdf?arnumber=11007207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T17:36:29Z","timestamp":1749144989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007207\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tim.2025.3571119","relation":{},"ISSN":["0018-9456","1557-9662"],"issn-type":[{"value":"0018-9456","type":"print"},{"value":"1557-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}