{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T08:04:25Z","timestamp":1768550665130,"version":"3.49.0"},"reference-count":62,"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":["62371343"],"award-info":[{"award-number":["62371343"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"name":"Hong Kong Research Grants Council","award":["GRF-15213322"],"award-info":[{"award-number":["GRF-15213322"]}]},{"name":"Hong Kong Research Grants Council","award":["GRF-15229423"],"award-info":[{"award-number":["GRF-15229423"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3385997","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T21:05:22Z","timestamp":1712610322000},"page":"9095-9108","source":"Crossref","is-referenced-by-count":4,"title":["Hybrid Graph Reasoning With Dynamic Interaction for Visual Dialog"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1048-4574","authenticated-orcid":false,"given":"Shanshan","family":"Du","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2244-0567","authenticated-orcid":false,"given":"Tengpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Chang Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990074"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230934"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3199603"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152086"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310332"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237164"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00684"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00639"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/693"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2992888"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.728"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6769"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3034494"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1209"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00506"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_20"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.269"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01757"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746098"},{"key":"ref31","first-page":"1","article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00843"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00939"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00144"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085755"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207228"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref50","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref51","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Corso","year":"2020"},{"key":"ref52","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref55","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref56","first-page":"314","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2017"},{"key":"ref57","first-page":"3722","article-title":"Visual reference resolution using attention memory for visual dialog","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Seo","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1648"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01068"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00265"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413826"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10494547.pdf?arnumber=10494547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T04:32:49Z","timestamp":1725078769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10494547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3385997","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}