{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T17:59:15Z","timestamp":1793123955938,"version":"4.5.0"},"reference-count":41,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01348","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14528-14537","source":"Crossref","is-referenced-by-count":4,"title":["MistSense: Versatile Online Detection of Procedural and Execution Mistakes"],"prefix":"10.1109","author":[{"given":"Constantin","family":"Patsch","sequence":"first","affiliation":[{"name":"Technical University of Munich, School of Computation, Information, and Technology,Chair of Media Technology, Munich Institute of Robotics and Machine Intelligence (MIRMI),Department of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuankai","family":"Wu","sequence":"additional","affiliation":[{"name":"Technical University of Munich, School of Computation, Information, and Technology,Chair of Media Technology, Munich Institute of Robotics and Machine Intelligence (MIRMI),Department of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marsil","family":"Zakour","sequence":"additional","affiliation":[{"name":"Technical University of Munich, School of Computation, Information, and Technology,Chair of Media Technology, Munich Institute of Robotics and Machine Intelligence (MIRMI),Department of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Driton","family":"Salihu","sequence":"additional","affiliation":[{"name":"Technical University of Munich, School of Computation, Information, and Technology,Chair of Media Technology, Munich Institute of Robotics and Machine Intelligence (MIRMI),Department of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eckehard","family":"Steinbach","sequence":"additional","affiliation":[{"name":"Technical University of Munich, School of Computation, Information, and Technology,Chair of Media Technology, Munich Institute of Robotics and Machine Intelligence (MIRMI),Department of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/computers11020028"},{"key":"ref3","article-title":"Video-mined task graphs for keystep recognition in instructional videos","volume":"36","author":"Ashutosh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-022-09831-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref7","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01749"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00347"},{"issue":"2","key":"ref12","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw.2019.00547"},{"key":"ref14","article-title":"Multimodal subtask graph generation from instructional videos","author":"Jang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/jj.25291671.13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01879-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01765"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92805-5_14"},{"key":"ref20","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref23","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref25","article-title":"Eyes wide unshut: Unsupervised mistake detection in egocentric procedural video by detecting unpredictable gaze","author":"Mazzamuto","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096960"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00689"},{"key":"ref28","article-title":"Ti-prego: Chain of thought and incontext learning for online mistake detection in procedural egocentric videos","author":"Plini","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00431"},{"key":"ref30","article-title":"Differentiable task graph learning: Procedural activity representation and online mistake detection from egocentric videos","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Seminara","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_25"},{"key":"ref33","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00776"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02035"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00316"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0330"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref41","article-title":"Antgpt: Can large language models help long-term action anticipation from videos?","author":"Zhao","year":"2024","journal-title":"ICLR"}],"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\/11444958.pdf?arnumber=11444958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:20Z","timestamp":1777529900000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01348","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}