{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T17:04:14Z","timestamp":1789837454608,"version":"4.0.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["62072116"],"award-info":[{"award-number":["62072116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Program Project","award":["21JC1400600"],"award-info":[{"award-number":["21JC1400600"]}]},{"name":"Shuguang Program"},{"DOI":"10.13039\/501100003024","name":"Shanghai Education Development Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Education Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3169065","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T19:33:51Z","timestamp":1650656031000},"page":"3950-3961","source":"Crossref","is-referenced-by-count":59,"title":["Scene Graph Refinement Network for Visual Question Answering"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3881-4857","authenticated-orcid":false,"given":"Tianwen","family":"Qian","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3148-264X","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoxiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6658-6452","authenticated-orcid":false,"given":"Bo","family":"Wu","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","article-title":"Be my eyes"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref5","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Adv. neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref11","first-page":"1564","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","article-title":"Understanding the role of scene graphs in visual question answering","author":"Damodaran","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00408"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00220"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475643"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3095196"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/454"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref33","first-page":"4272","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref35","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref36","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref37","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref41","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wu","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref45","first-page":"1031","article-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yi","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037461"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.555"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00718"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01459"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108455"},{"key":"ref62","first-page":"5903","article-title":"Learning by abstraction: The neural state machine","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Hudson","year":"2019"},{"key":"ref63","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statistics. JMLR Workshop Conf. Proc.","author":"Glorot","year":"2011"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref65","first-page":"5998","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","year":"2017"},{"key":"ref66","article-title":"Compositional attention networks for machine reasoning","author":"Hudson","year":"2018"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413998"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00070"},{"key":"ref72","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref74","article-title":"Graph attention networks","author":"Velikovi","year":"2017"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390709"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09762027.pdf?arnumber=9762027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T20:55:46Z","timestamp":1705956946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3169065","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}