{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T08:13:09Z","timestamp":1781165589228,"version":"3.54.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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","award":["U22A2094"],"award-info":[{"award-number":["U22A2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272144"],"award-info":[{"award-number":["62272144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72188101"],"award-info":[{"award-number":["72188101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272435"],"award-info":[{"award-number":["62272435"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Anhui Province","award":["2408085J040"],"award-info":[{"award-number":["2408085J040"]}]},{"name":"Major Project of Anhui Province","award":["202203a05020011"],"award-info":[{"award-number":["202203a05020011"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024HGTG0309"],"award-info":[{"award-number":["JZ2024HGTG0309"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024AHST0337"],"award-info":[{"award-number":["JZ2024AHST0337"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2023YQTD0072"],"award-info":[{"award-number":["JZ2023YQTD0072"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3639956","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:35Z","timestamp":1765219295000},"page":"1417-1430","source":"Crossref","is-referenced-by-count":3,"title":["Scene-Text Grounding for Text-Based Video Question Answering"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4215-5464","authenticated-orcid":false,"given":"Sheng","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5573-6195","authenticated-orcid":false,"given":"Junbin","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-3375","authenticated-orcid":false,"given":"Peipei","family":"Song","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7418-6141","authenticated-orcid":false,"given":"Angela","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01405"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611753"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3607810"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3352002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"ref19","first-page":"25663","article-title":"Gomatching: A simple baseline for video text spotting via long and short term matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00442"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303451"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01275"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126916"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3215887"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref33","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2019"},{"key":"ref34","article-title":"GPT-4O MINI: Advancing cost-efficient intelligence","author":"Menick","year":"2024","journal-title":"Open AI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.maiworkshop-1.4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612299"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41731-3_9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref44","article-title":"Qwen2-VL: Enhancing vision-language models perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611769"},{"key":"ref46","article-title":"A bilingual, openworld video text dataset and end-to-end video text spotter with transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (Datasets Benchmarks Track)","author":"Wu","year":"2021."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_27"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4084-6"},{"key":"ref52","first-page":"76749","article-title":"Self-chained image-language model for video localization and question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2024"},{"key":"ref53","article-title":"VIDATANU CVML video annotation tool","author":"Zhang","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387696"},{"key":"ref55","first-page":"35549","article-title":"Towards video text visual question answering: Benchmark and baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310332"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3634918"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00319"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969791"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26357"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11285117.pdf?arnumber=11285117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:30Z","timestamp":1773086370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11285117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3639956","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}