{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:12:13Z","timestamp":1781622733265,"version":"3.54.5"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2021YFF0901600"],"award-info":[{"award-number":["2021YFF0901600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176074"],"award-info":[{"award-number":["62176074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Interdisciplinary Development Program of Harbin Institute of Technology","award":["SYL-JC-202203"],"award-info":[{"award-number":["SYL-JC-202203"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2022FRFK0600XX"],"award-info":[{"award-number":["2022FRFK0600XX"]}],"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":[[2024]]},"DOI":"10.1109\/tmm.2023.3326616","type":"journal-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:15:18Z","timestamp":1698084918000},"page":"8348-8359","source":"Crossref","is-referenced-by-count":2,"title":["CroMIC-QA: The Cross-Modal Information Complementation Based Question Answering"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2443-2954","authenticated-orcid":false,"given":"Shun","family":"Qian","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6352-2170","authenticated-orcid":false,"given":"Bingquan","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9081-1410","authenticated-orcid":false,"given":"Chengjie","family":"Sun","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9688-6958","authenticated-orcid":false,"given":"Zhen","family":"Xu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8995-7543","authenticated-orcid":false,"given":"Baoxun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Company, Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"595","article-title":"Multimodal neural language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kiros","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref14","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref15","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref17","first-page":"8601","article-title":"Self-critical reasoning for robust visual question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Wu","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01251"},{"key":"ref20","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Karpathy","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2028"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref55","volume-title":"Modern Information Retrieval","volume":"463.","author":"Baeza-Yates","year":"1999"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330677"},{"key":"ref57","first-page":"77","article-title":"The trec-8 question answering track report","volume-title":"Proc. Trec","author":"Voorhees","year":"1999"},{"key":"ref58","volume-title":"Introduction to Information Retrieval","volume":"39.","author":"Schtze","year":"2008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref61","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"ref62","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref66","article-title":"MultiModalQA: Complex question answering over text, tables and images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Talmor","year":"2020"},{"key":"ref67","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054758"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.129"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00800"},{"key":"ref72","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462838"},{"key":"ref75","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.035"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_13"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"ref82","article-title":"Chinese CLIP: Contrastive vision-language pretraining in Chinese","author":"Yang","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10290942.pdf?arnumber=10290942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T08:12:00Z","timestamp":1722586320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10290942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3326616","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}