{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:09:53Z","timestamp":1770743393394,"version":"3.49.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3558429","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:59:37Z","timestamp":1744063177000},"page":"85084-85097","source":"Crossref","is-referenced-by-count":1,"title":["Visual Commonsense Causal Reasoning From a Still Image"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4064-9720","authenticated-orcid":false,"given":"Xiaojing","family":"Wu","sequence":"first","affiliation":[{"name":"School of Undergraduate Education, Shenzhen Polytechnic University, Shenzhen, China"}]},{"given":"Rui","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Beijing Polytechnic College, Beijing, China"}]},{"given":"Qin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Weifang Engineering Vocational College, Qingzhou, Shandong, China"}]},{"given":"Ning","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shangyu Technology (Beijing) Company Ltd., Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315081656"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107347"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref8","first-page":"26750","article-title":"ROCK: Causal inference principles for reasoning about commonsense causality","volume-title":"Proc. ICML","author":"Zhang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.288"},{"key":"ref10","first-page":"421","article-title":"Commonsense causal reasoning between short texts","volume-title":"Proc. KR","author":"Luo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_30"},{"key":"ref12","first-page":"1","article-title":"Causal parrots: Large language models may talk causality but are not causal","volume":"8","author":"Zecevic","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10516-023-09671-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2307\/2289069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/82.4.669"},{"issue":"2","key":"ref16","first-page":"3","volume-title":"Models, Reasoning and Inference","volume":"19","author":"Pearl","year":"2000"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000001880"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139025751"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107587991"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.4135\/9781412952637.n77"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2005.00377.x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1903"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6207"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/09-STS313"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwq439"},{"key":"ref27","first-page":"1","article-title":"Visual choice of plausible alternatives: An evaluation of image-based commonsense causal reasoning","volume-title":"Proc. LREC","author":"Yeo"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475328"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.640"},{"key":"ref31","volume":"11","author":"Guo","year":"2014","journal-title":"Propensity Score Analysis: Statistical Methods and Applications"},{"key":"ref32","volume-title":"Propensity Score Analysis: Fundamentals and Developments","author":"Pan","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2016.1260466"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/70.1.41"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1984.10478078"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/1536867X0400400307"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1043"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-tutorials.7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1135"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.20"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6004"},{"key":"ref43","article-title":"Can large language models infer causation from correlation?","author":"Jin","year":"2023","journal-title":"arXiv:2306.05836"},{"key":"ref44","first-page":"2097","article-title":"An analysis of causality between events and its relation to temporal information","volume-title":"Proc. COLING","author":"Mirza"},{"key":"ref45","first-page":"294","article-title":"Minimally supervised event causality identification","volume-title":"Proc. EMNLP","author":"Do"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1037\/rev0000281"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00511"},{"key":"ref48","first-page":"1026","article-title":"Some reflections on drawing causal inference using textual data: Parallels between human subjects and organized texts","volume-title":"Proc. Conf. Causal Learn. Reasoning","author":"Zhang"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref50","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref51","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref52","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref53","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref55","article-title":"ChatGPT is a knowledgeable but inexperienced solver: An investigation of commonsense problem in large language models","author":"Bian","year":"2023","journal-title":"arXiv:2303.16421"},{"key":"ref56","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. ICML","author":"Zeng"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref62","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.399"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref65","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.2307\/2981697"},{"key":"ref68","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6419.2007.00527.x"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1987.10478441"},{"key":"ref71","volume-title":"Semiparametric Theory and Missing Data","author":"Tsiatis","year":"2007"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12027"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/pan\/mpj004"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1994.10476818"},{"key":"ref75","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. NeurIPS","volume":"34","author":"Tsimpoukelli"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.523"},{"key":"ref77","article-title":"Scaling instruction-finetuned language models","author":"Won Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref78","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.357"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10950140.pdf?arnumber=10950140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T06:20:59Z","timestamp":1747808459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10950140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3558429","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}