{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T12:00:51Z","timestamp":1768910451294,"version":"3.49.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ant Group Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tbdata.2025.3600012","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:17:24Z","timestamp":1755627444000},"page":"47-61","source":"Crossref","is-referenced-by-count":1,"title":["TAG: Triple Alignment With Rationale Generation for Knowledge-Based Visual Question Answering"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8693-7142","authenticated-orcid":false,"given":"Sihang","family":"Cai","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingtong","family":"Wu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Jin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"8","key":"ref5","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref7","first-page":"2659","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Narasimhan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref18","article-title":"PromptCap: Prompt-guided task-aware image captioning","author":"Hu","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref21","article-title":"REVIVE: Regional visual representation matters in knowledge-based visual question answering","author":"Lin","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref25","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref27","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3173131"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3190686"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3272224"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289729"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292597"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05981-0_1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02059"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3051277"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.122"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548035"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01275"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref63","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref66","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref68","first-page":"4489","article-title":"Unsupervised learning of dense visual representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pinheiro"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01086"},{"key":"ref71","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref73","article-title":"Multi-modal semantic understanding with contrastive cross-modal feature alignment","author":"Zhang","year":"2024"},{"key":"ref74","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Alexey"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"ref76","article-title":"Bidirectional attention flow for machine comprehension","author":"Seo","year":"2016"},{"key":"ref77","article-title":"QANet: Combining local convolution with global self-attention for reading comprehension","author":"Yu","year":"2018"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref82","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref84","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gan"},{"key":"ref85","article-title":"ClipCap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref86","first-page":"5100","article-title":"LXMERT: Learning cross-modality encoder representations from transformers","volume-title":"Proc. 2019 Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process.","author":"Tan"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11357241\/11129918.pdf?arnumber=11129918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:56:13Z","timestamp":1768856173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11129918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":86,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2025.3600012","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}