{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:48Z","timestamp":1778048328448,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00658","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6806-6817","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data"],"prefix":"10.1109","author":[{"given":"Ivo","family":"Bueno","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruikun","family":"Hou","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Babette","family":"B\u00fchler","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"F\u00fctterer","sequence":"additional","affiliation":[{"name":"University of Tübingen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Drimalla","sequence":"additional","affiliation":[{"name":"Gordon College"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan K.","family":"Foster","sequence":"additional","affiliation":[{"name":"University at Albany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Youngs","sequence":"additional","affiliation":[{"name":"University of Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Gerjets","sequence":"additional","affiliation":[{"name":"Leibniz-Institut für Wissensmedien"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrich","family":"Trautwein","sequence":"additional","affiliation":[{"name":"University of Tübingen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enkelejda","family":"Kasneci","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3351229"},{"key":"ref2","article-title":"Introducing llama 3.1: Our most capable models to date, 2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref4","article-title":"V-jepa 2: Self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025"},{"key":"ref5","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref6","article-title":"Revisiting feature prediction for learning visual representations from video","author":"Bardes","year":"2024"},{"key":"ref7","article-title":"Annex a: Talis video observation codes: Holistic domain ratings and components","volume-title":"Technical report","author":"Bell","year":"2018"},{"key":"ref8","article-title":"Asymmetric loss for multi-label classification","author":"Ben-Baruch","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref10","first-page":"104","article-title":"Automated visual attention detection using mobile eye tracking in behavioral classroom studies","volume-title":"Proceedings of the 18th International Conference on Educational Data Mining","author":"Bozkir"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36272-9_9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-024-00412-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11233998"},{"key":"ref16","article-title":"Weakly supervised data augmentation through prompting for dialogue understanding","author":"Chen","year":"2022"},{"key":"ref17","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.44"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3102\/01623737231169270"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-98420-4_14"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2024.100207"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18608\/jla.2024.8323"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2025.100483"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.learninstruc.2025.102264"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10648-019-09514-z"},{"key":"ref30","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref32","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","author":"He","year":"2021"},{"key":"ref33","article-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing","author":"He","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-64302-6_5"},{"key":"ref35","first-page":"241","article-title":"Multi-modal assessment of classroom discourse quality: A text-centered attention-based multi-task learning approach","volume-title":"Proceedings of the 18th International Conference on Educational Data Mining","author":"Hou"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3102\/0034654318759268"},{"key":"ref38","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref40","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41539-024-00273-3"},{"key":"ref42","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref44","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3059209"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3706468.3706527"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.824"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/EDFP_a_00173"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/089120100561737"},{"key":"ref52","first-page":"2315","article-title":"Teachers\u2019 perception in the classroom","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"Sumer"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3127692"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref55","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijer.2023.102275"},{"key":"ref58","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103646"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3595170"},{"key":"ref61","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Wei"},{"key":"ref62","article-title":"Automated evaluation of classroom instructional support with llms and bows: Connecting global predictions to specific feedback","author":"Whitehill","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.63317\/5pwa5zpssv4z"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.tate.2021.103576"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101670"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492357.pdf?arnumber=11492357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:08Z","timestamp":1778046968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00658","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}