{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:28:53Z","timestamp":1770917333038,"version":"3.50.1"},"reference-count":55,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91748122"],"award-info":[{"award-number":["91748122"]}],"id":[{"id":"10.13039\/501100001809","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.2023.3347093","type":"journal-article","created":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T19:27:53Z","timestamp":1703618873000},"page":"6202-6214","source":"Crossref","is-referenced-by-count":9,"title":["LOIS: Looking Out of Instance Semantics for Visual Question Answering"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0001-0204","authenticated-orcid":false,"given":"Siyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5515-1943","authenticated-orcid":false,"given":"Yeming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-0713","authenticated-orcid":false,"given":"Yaoru","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1987-9150","authenticated-orcid":false,"given":"Fang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Brunel University, Uxbridge, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9976-6927","authenticated-orcid":false,"given":"Haibo","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4622-0119","authenticated-orcid":false,"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26569"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475234"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-06923-0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00197"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3302162"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref16","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref19","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3093725"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3101642"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018997"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3017530"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.05.001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6389-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3029423"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830"},{"key":"ref38","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"Proc. NAACL-HLT"},{"key":"ref39","first-page":"17721","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref41","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2017","journal-title":"Proc. Int. Conf. Learn. Represent."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2998805"},{"key":"ref45","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref46","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref47","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Su","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref51","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3160418"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105284"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/126"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10374273.pdf?arnumber=10374273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T19:06:49Z","timestamp":1712862409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10374273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3347093","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}