{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T18:18:41Z","timestamp":1781806721885,"version":"3.54.5"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS 2348689"],"award-info":[{"award-number":["IIS 2348689"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS 2348690"],"award-info":[{"award-number":["IIS 2348690"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000199","name":"U.S. Department of Agriculture","doi-asserted-by":"publisher","award":["2023-69014-39716-1030191"],"award-info":[{"award-number":["2023-69014-39716-1030191"]}],"id":[{"id":"10.13039\/100000199","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/lra.2025.3583626","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:45:09Z","timestamp":1750959909000},"page":"8220-8227","source":"Crossref","is-referenced-by-count":1,"title":["EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9388-5117","authenticated-orcid":false,"given":"Zhou","family":"Chen","sequence":"first","affiliation":[{"name":"CSSE Department, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjoy","family":"Kundu","sequence":"additional","affiliation":[{"name":"CSSE Department, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsimran S.","family":"Baweja","sequence":"additional","affiliation":[{"name":"School of Kinesiology, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1062-8929","authenticated-orcid":false,"given":"Sathyanarayanan N.","family":"Aakur","sequence":"additional","affiliation":[{"name":"CSSE Department, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning hierarchical world models with adaptive temporal abstractions from discrete latent dynamics","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Gumbsch","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.127.1.3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-18207-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78354-8_19"},{"key":"ref7","article-title":"AD-VAT: An asymmetric dueling mechanism for learning visual active tracking","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhong","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952590"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE48301.2019.9043821"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5220\/0010236807320741"},{"key":"ref12","first-page":"3286","article-title":"End-to-end active object tracking via reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo","year":"2017"},{"key":"ref13","first-page":"12782","article-title":"Towards distraction-robust active visual tracking","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhong","year":"2021"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v34i01.5419","article-title":"Pose-assisted multi-camera collaboration for active object tracking","author":"Li","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01420-x"},{"key":"ref16","article-title":"AD-VAT: An asymmetric dueling mechanism for learning visual active tracking","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhong","year":"2018"},{"key":"ref17","first-page":"263","article-title":"Pointly-supervised action localization","volume-title":"Int. J. Comput. Vis.","volume":"127","author":"Mettes","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00560"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00276"},{"key":"ref22","article-title":"Can MLLMs guide weakly-supervised temporal action localization tasks?","author":"Zhang","year":"2024"},{"key":"ref23","first-page":"48","article-title":"Spatio-temporal event segmentation for wildlife extended videos","volume-title":"Proc. Int. Conf. Comput. Vis. Image Process.","author":"Mounir","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5220\/0010288009350942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02191"},{"key":"ref26","first-page":"840","article-title":"Colorization as a proxy task for visual understanding","volume-title":"Proc. 2017 IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Larsson","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00092"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref29","article-title":"Video representation learning with visual tempo consistency","author":"Yang","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00358"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2787"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-012-0512-8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3049907"},{"key":"ref36","article-title":"Active inference in robotics and artificial agents: Survey and challenges","author":"Lanillos","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2018.01.009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/12441.001.0001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/e24020301"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3477306"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/e25111506"},{"key":"ref42","first-page":"351","article-title":"Playing atari with deep reinforcement learning","volume":"21","author":"Chung","year":"2013","journal-title":"Comput. Ence"},{"issue":"268","key":"ref43","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3129396"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2899570"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/11045364\/11052728-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11045364\/11052728.pdf?arnumber=11052728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T17:40:06Z","timestamp":1751996406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11052728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":47,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3583626","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}