{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:24:10Z","timestamp":1783110250044,"version":"3.54.6"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology Major Project - Mobile Information Networks","award":["2024ZD1300700"],"award-info":[{"award-number":["2024ZD1300700"]}]},{"name":"Natural Science Foundation","award":["62293483"],"award-info":[{"award-number":["62293483"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3664986","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:48Z","timestamp":1771276068000},"page":"5380-5394","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Scene Graph Generation With Coarse-to-Fine Reasoning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7773-3834","authenticated-orcid":false,"given":"Zefang","family":"Han","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiukun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7857-0845","authenticated-orcid":false,"given":"Xuemei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4718-9360","authenticated-orcid":false,"given":"Jianxiu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanxi Datong University, Datong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2179-3292","authenticated-orcid":false,"given":"Guangming","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3443661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169065"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664816"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463650"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA210049"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00184"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00819"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02674"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2990989"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297842"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3344569"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3130197"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3282349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01978"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193857"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_27"},{"key":"ref26","first-page":"2284","article-title":"Text generation from knowledge graphs with graph transformers","volume-title":"Proc. NAACL-HLT","author":"Koncel-Kedziorski","year":"2019"},{"key":"ref27","article-title":"SceneGPT: A language model for 3D scene understanding, 2024","author":"Chandhok"},{"key":"ref28","article-title":"SGL-PT: A strong graph learner with graph prompt tuning","author":"Guo","year":"2025","journal-title":"SSRN Electron. J."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02667"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00861"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02564-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_12"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"issue":"1","key":"ref38","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"2","author":"Bai","year":"2023","journal-title":"Text Reading and beyond"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref42","article-title":"Visual chatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3149"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1657"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00266"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00620"},{"key":"ref50","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3785474"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11397185.pdf?arnumber=11397185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:53:41Z","timestamp":1783108421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3664986","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}