{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:18:42Z","timestamp":1792790322394,"version":"4.5.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"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":["U19B2039"],"award-info":[{"award-number":["U19B2039"]}],"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":["62172023"],"award-info":[{"award-number":["62172023"]}],"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":["62206007"],"award-info":[{"award-number":["62206007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002888","name":"Research and Development Program of Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KZ202210005008"],"award-info":[{"award-number":["KZ202210005008"]}],"id":[{"id":"10.13039\/501100002888","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4222021"],"award-info":[{"award-number":["4222021"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Engineering Research Center of Intelligent Perception and Autonomous Control, Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tcsvt.2023.3291379","type":"journal-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T14:30:59Z","timestamp":1688394659000},"page":"1135-1146","source":"Crossref","is-referenced-by-count":34,"title":["See and Learn More: Dense Caption-Aware Representation for Visual Question Answering"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5377-8965","authenticated-orcid":false,"given":"Yandong","family":"Bi","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1158-6321","authenticated-orcid":false,"given":"Huajie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0440-438X","authenticated-orcid":false,"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0872-384X","authenticated-orcid":false,"given":"Yanfeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.09.008"},{"key":"ref2","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref4","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and VQA","volume-title":"Proc. CVPR","author":"Anderson"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2940647"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01459"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00419"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref13","first-page":"5901","article-title":"Learning by abstraction: The neural state machine","volume-title":"Proc. NeurIPS","author":"Hudson"},{"key":"ref14","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref17","first-page":"13","article-title":"VilBERT: Pretraining taskagnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref21","first-page":"8601","article-title":"Self-critical reasoning for robust visual question answering","volume-title":"Proc. NeurIPS","volume":"32","author":"Wu"},{"key":"ref22","first-page":"839","article-title":"RUBi: Reducing unimodal biases in visual question answering","volume-title":"Proc. NeurIPS","author":"Cadene"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref24","first-page":"1548","article-title":"Overcoming language priors in visual question answering with adversarial regularization","volume-title":"Proc. NeurIPS","volume":"31","author":"Ramakrishnan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17034"},{"key":"ref33","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. ICML","author":"Cho"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189242"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1348"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11276-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1351"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.643"},{"key":"ref40","first-page":"91","article-title":"Faster R-CNN: Towards realtime object detection with region proposal networks","volume-title":"Proc. NeurIPS","volume":"28","author":"Ren"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00070"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref48","first-page":"18","article-title":"Reducing language biases in visual question answering with visually-grounded question encoder","volume-title":"Proc. ECCV","author":"Mittal"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1418"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00145"},{"key":"ref52","first-page":"407","article-title":"On the value of out-of-distribution testing: An example of goodhart\u2019s law","volume-title":"Proc. NeurIPS","volume":"33","author":"Teney"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref54","article-title":"ExpansionNet v2: Block static expansion in fast end to end training for image captioning","author":"Hu","year":"2022","journal-title":"arXiv:2208.06551"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10422872\/10171793.pdf?arnumber=10171793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T15:09:55Z","timestamp":1736435395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10171793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":54,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3291379","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}