{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T06:09:28Z","timestamp":1775628568857,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00148","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"984-989","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Contrastive Learning for Understanding Procedural Activities"],"prefix":"10.1109","author":[{"given":"Chenxi","family":"Guo","sequence":"first","affiliation":[{"name":"University of Applied Sciences Aschaffenburg,Germany"}]},{"given":"Andreas","family":"Hubert","sequence":"additional","affiliation":[{"name":"University of Applied Sciences Aschaffenburg,Germany"}]},{"given":"Konrad","family":"Doll","sequence":"additional","affiliation":[{"name":"University of Applied Sciences Aschaffenburg,Germany"}]}],"member":"263","reference":[{"key":"ref1","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref2","article-title":"Understanding intermediate layers using linear classifier probes","author":"Alain","year":"2016"},{"key":"ref3","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"Alayrac","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3315"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298599"},{"key":"ref10","article-title":"Concept-Fusion: Open-set multimodal 3D mapping","author":"Jatavallabhula","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref12","article-title":"Temperature schedules for self-supervised contrastive methods on long-tail data","author":"Kukleva","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref14","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref15","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref18","article-title":"Contrastive learning with hard negative samples","author":"Robinson","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610095"},{"key":"ref24","article-title":"VideoCLIP: Contrastive pretraining for zero-shot video-text understanding","author":"Xu","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01424"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01033"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3166397"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iceet65156.2024.10913824"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196714"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471498.pdf?arnumber=11471498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:32:33Z","timestamp":1775626353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00148","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}