{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:42:00Z","timestamp":1768423320725,"version":"3.49.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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"}]},{"DOI":"10.13039\/501100010256","name":"Shanghai Municipal Science and Technology Major","doi-asserted-by":"publisher","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3428487","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T18:53:03Z","timestamp":1721069583000},"page":"11682-11694","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3835-4627","authenticated-orcid":false,"given":"Jian","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology and the Key Laboratory of Embedded System and Service Computing (Ministry of Education), 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 and the Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4933-0073","authenticated-orcid":false,"given":"Miaojing","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3079278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165934"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref9","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref10","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref11","first-page":"2769","article-title":"Heterogeneous graph learning for visual commonsense reasoning","volume-title":"Proc. NeurIPS\u201919","author":"Yu"},{"key":"ref12","first-page":"15615","article-title":"TAB-VCR: Tags and attributes based vcr baselines","volume-title":"Proc. NeurIPS\u201919","author":"Lin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475328"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref18","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. ICLR\u201920","author":"Su"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref20","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","volume-title":"Proc. NeurIPS\u201919","author":"Wu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3279691"},{"key":"ref22","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286259"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275874"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW60847.2023.00074"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982280"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3205446"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897161"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942928"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR\u201914","author":"Kingma"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. ICLR\u201917","author":"Kim"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16428"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768851\/10599309.pdf?arnumber=10599309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:48:37Z","timestamp":1734551317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10599309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3428487","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}