{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T21:14:25Z","timestamp":1776719665725,"version":"3.51.2"},"reference-count":64,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576206"],"award-info":[{"award-number":["62576206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476089"],"award-info":[{"award-number":["62476089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Key Laboratory of System Control and Information Processing"},{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund of Key Laboratory of Advanced Theory and Application in Statistics and Data Science"},{"DOI":"10.13039\/501100004106","name":"East China Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004106","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651070","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"2719-2730","source":"Crossref","is-referenced-by-count":0,"title":["Visual Context and Commonsense-Guided Causal Chain-of-Thoughts for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9059-5090","authenticated-orcid":false,"given":"Xinyu","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-5330","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7421-1711","authenticated-orcid":false,"given":"Tongquan","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7069-3752","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14299.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.99"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16792"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3206505"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.225"},{"key":"ref9","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191699"},{"key":"ref11","article-title":"Exploring ways to incorporate additional knowledge to improve natural language commonsense question answering","author":"Mitra","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref13","first-page":"11338","article-title":"Localized symbolic knowledge distillation for visual commonsense models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Park","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17593"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.163"},{"key":"ref16","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref17","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref18","article-title":"LLAMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.640"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.68"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129806"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.49"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521725"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-tutorials.7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3279691"},{"key":"ref29","first-page":"1","article-title":"Multimodal chain-of-thought reasoning in language models","volume":"5","author":"Zhang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref30","article-title":"Eventlens: Leveraging event-aware pretraining and cross-modal linking enhances visual commonsense reasoning","author":"Ma","year":"2024"},{"key":"ref31","article-title":"Machine common sense concept paper","author":"Gunning","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3276505"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3386339"},{"key":"ref34","first-page":"61747","article-title":"Causal-IQA: Towards the generalization of image quality assessment based on causal inference","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhong","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3231338"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0546"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.288"},{"key":"ref38","first-page":"1","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2023","journal-title":"Proc. 11th Int. Conf. Learn. Representations"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2956775"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_12"},{"key":"ref41","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"issue":"70","key":"ref42","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref44","first-page":"1","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3692-2_3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000001880"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.523"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.117"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/70.1.41"},{"key":"ref51","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2018"},{"key":"ref52","first-page":"26750","article-title":"Rock: Causal inference principles for reasoning about commonsense causality","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref55","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref57","article-title":"MPLUG-OWL: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref58","article-title":"QWEN-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_30"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_32"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref63","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329490.pdf?arnumber=11329490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:33Z","timestamp":1776715533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651070","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}