{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:52Z","timestamp":1777888672170,"version":"3.51.4"},"reference-count":53,"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\/iccv51701.2025.01298","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13985-13994","source":"Crossref","is-referenced-by-count":0,"title":["RobAVA: A Large-Scale Dataset and Baseline Towards Video Based Robotic Arm Action Understanding"],"prefix":"10.1109","author":[{"given":"Baoli","family":"Sun","sequence":"first","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinzhu","family":"Ma","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anqi","family":"Zou","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihang","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuixuan","family":"Fan","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,Liaoning,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney,Sydney,New South Wales,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3643458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref4","article-title":"Is space-time attention all you need for video understanding? In ICML, July, Virtual Event, pages 813\u2013824, 2021","author":"Bertasius","journal-title":"3"},{"key":"ref5","first-page":"4724","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","year":"2017","journal-title":"In IEEE\/CVF, CVPR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3400189"},{"key":"ref7","article-title":"GENOME: generative neuro-symbolic visual reasoning by growing and reusing modules","author":"Chen","year":"2024","journal-title":"In ICLR"},{"key":"ref8","first-page":"885","article-title":"Robonet: Large-scale multi-robot learning","volume-title":"In Conference on Robot Learning, CoRL","author":"Dasari","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref11","first-page":"8469","article-title":"al","author":"Driess","year":"2023","journal-title":"Palm-e: An embodied multimodal language model. In ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref13","article-title":"Lee, and Sergey Levine","volume":"abs\/1812.00568","author":"Ebert","year":"2018","journal-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control. CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560844"},{"key":"ref15","first-page":"12","article-title":"VSE++: improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2018","journal-title":"In BMVC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref18","first-page":"466","article-title":"Objectfolder: A dataset of objects with implicit visual, auditory, and tactile representations","volume-title":"In Conference on Robot Learning","author":"Gao","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2904558"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3038072"},{"key":"ref23","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume":"abs\/2409.01652","author":"Huang","year":"2024","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3322276.3322343"},{"key":"ref28","article-title":"Uniformer: Unified transformer for efficient spatial-temporal representation learning","author":"Li","year":"2022","journal-title":"In ICLR"},{"key":"ref29","first-page":"5373","article-title":"UniFormerV2: spatiotemporal learning by arming image vits with video uniformer","author":"Li","year":"2023","journal-title":"In IEEE\/CVF, ICCV"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112190"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref36","first-page":"1820","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","volume-title":"In Conference on Robot Learning, CoRL","author":"Mandlekar","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957814"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3029798.3038373"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref40","first-page":"6892","article-title":"Open xembodiment: Robotic learning datasets and RT-X models: Open x-embodiment collaboration","author":"O\u2019Neill","year":"2024","journal-title":"In IEEE, ICRA, May"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"In ICML"},{"key":"ref42","first-page":"1838","article-title":"Latent plans for taskagnostic offline reinforcement learning","volume-title":"In Conference on Robot Learning, CoRL","author":"Rosete-Beas","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref44","article-title":"Large language models still can\u2019t plan (A benchmark for 11 ms on planning and reasoning about change)","volume":"abs\/2206.10498","author":"Valmeekam","year":"2022","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref46","article-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers","volume":"abs\/2409.20537","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref47","article-title":"Actionclip: A new paradigm for video action recognition","volume":"abs\/2109.08472","author":"Wang","year":"2021","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2016.7758091"},{"key":"ref52","article-title":"al","volume":"abs\/2111.11432","author":"Yuan","year":"2021","journal-title":"Florence: A new foundation model for computer vision. CoRR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517449"}],"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\/11444384.pdf?arnumber=11444384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:51:42Z","timestamp":1777611102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01298","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}