{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:49Z","timestamp":1778051509979,"version":"3.51.4"},"reference-count":54,"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\/wacv61042.2026.00280","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2858-2868","source":"Crossref","is-referenced-by-count":0,"title":["STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences"],"prefix":"10.1109","author":[{"given":"Soroush","family":"Mehraban","sequence":"first","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Javad","family":"Rajabi","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Iaboni","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Babak","family":"Taati","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01767"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref4","article-title":"BEiT: Bert pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"ref8","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref11","article-title":"DGSTGCN: dynamic spatial-temporal modeling for skeleton-based action recognition","author":"Duan","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref14","article-title":"Hyperbolic self-paced learning for self-supervised skeleton-based action representations","author":"Franco","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/95"},{"key":"ref20","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"ref23","article-title":"Contrastive tuning: A little help to make masked autoencoders forget","author":"Lehner","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02415-5"},{"key":"ref32","article-title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","author":"Mishra","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/GET.2016.7916786"},{"key":"ref34","author":"Park","year":"2023","journal-title":"What do self-supervised vision transformers learn?"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01807"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.115"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612449"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"},{"key":"ref41","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"33","author":"Tian","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/200"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2660505.2660512"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3724\/sp.j.2096-5796.2018.0006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25451"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611774"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"ref52","article-title":"iBOT: Image bert pre-training with online tokenizer","author":"Zhou","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25495"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01385"}],"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\/11492424.pdf?arnumber=11492424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:15:03Z","timestamp":1778048103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00280","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}