{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T22:35:58Z","timestamp":1784673358490,"version":"3.55.0"},"reference-count":105,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DRL-2112635"],"award-info":[{"award-number":["DRL-2112635"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["113-2628-E-A49-022,114-2628-E-A49-007"],"award-info":[{"award-number":["113-2628-E-A49-022,114-2628-E-A49-007"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01143","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12294-12306","source":"Crossref","is-referenced-by-count":2,"title":["What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning"],"prefix":"10.1109","author":[{"given":"Chi-Hsi","family":"Kung","sequence":"first","affiliation":[{"name":"Indiana University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frangil","family":"Ramirez","sequence":"additional","affiliation":[{"name":"Indiana University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhyung","family":"Ha","sequence":"additional","affiliation":[{"name":"Indiana University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"National Yang-Ming Chiao-Tung University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Crandall","sequence":"additional","affiliation":[{"name":"Indiana University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Hsuan","family":"Tsai","sequence":"additional","affiliation":[{"name":"Atmanity Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02209"},{"key":"ref3","article-title":"Video-mined task graphs for keystep recognition in instructional videos","volume":"36","author":"Ashutosh","year":"2024","journal-title":"Neural Information Processing Systems"},{"key":"ref4","article-title":"To ask or not to ask: Human-in-the-loop contextual bandits with applications in robotassisted feeding","author":"Banerjee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00638"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01844"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref10","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247259"},{"key":"ref12","article-title":"Scaling egocentric vision: The epickitchens dataset","volume-title":"European Conference on Computer Vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00957"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"ref17","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.333"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(96)00715-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.052"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1145\/3610977.3634975","article-title":"Feel the bite: Robot-assisted inside-mouth bite transfer using robust mouth perception and physical interaction-aware control","volume-title":"Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Kumar Jenamani","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"ref29","article-title":"Supervised contrastive learning","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Khosla"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref31","article-title":"Wikihow: A large scale text summarization dataset","author":"Koupaee","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref33","article-title":"Riskbench: A scenario-based benchmark for risk identification","author":"Kung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01746"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_11"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3117"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01765"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02059"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00945"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"ref42","article-title":"Egocentric video-language pretraining","author":"Qinghong Lin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.318"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01333"},{"key":"ref47","article-title":"Neurosymbolic procedural planning with commonsense prompting","author":"Yujie","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01780"},{"key":"ref52","article-title":"Learning and verification of task structure in instructional videos","author":"Narasimhan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Schema: State changes matter for procedure planning in instructional videos","author":"Niu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01345"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128834"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.121.1.133"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01852"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref62","article-title":"Reliable decision support using counterfactual models","volume":"30","author":"Schulam","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref63","article-title":"Differentiable task graph learning: Procedural activity representation and online mistake detection from egocentric videos","author":"Seminara","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"ref67","article-title":"Learning visually-grounded semantics from contrastive adversarial samples","author":"Shi","year":"2018","journal-title":"arXiv preprint"},{"key":"ref68","author":"Sigurdsson","year":"2018","journal-title":"Charades-ego: A largescale dataset of paired third and first person videos"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01357"},{"key":"ref71","article-title":"Multi-task learning of object state changes from uncurated videos","author":"Sou\u010dek","year":"2022","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00627"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362288"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475472"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01248"},{"key":"ref79","article-title":"Mosaic: A modular system for assistive and interactive cooking","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00293"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_42"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00950"},{"key":"ref87","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"ref89","first-page":"3536","article-title":"Xskill: Cross embodiment skill discovery","volume-title":"Conference on robot learning","author":"Xu","year":"2023"},{"key":"ref90","article-title":"Learning finegrained view-invariant representations from unpaired egoexo videos via temporal alignment","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Xue","year":"2023"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01750"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610050"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.49"},{"key":"ref95","article-title":"Clevrer: Collision events for video representation and reasoning","volume-title":"International Conference on Learning Representations","author":"Yi","year":"2020"},{"key":"ref96","first-page":"537","article-title":"Xirl: Crossembodiment inverse reinforcement learning","volume-title":"Conference on Robot Learning","author":"Zakka","year":"2022"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.915"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02064"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/182"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01424"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"ref105","article-title":"Vision-based manipulation from single human video with open-world object graphs","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444751.pdf?arnumber=11444751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:28Z","timestamp":1777612048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01143","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}