{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:13Z","timestamp":1792786933625,"version":"4.5.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key R&D Program of Shandong Province","award":["2025CXGC010111"],"award-info":[{"award-number":["2025CXGC010111"]}]},{"name":"National Natural Science Foundation of China","award":["U22A2057"],"award-info":[{"award-number":["U22A2057"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3676664","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:09:08Z","timestamp":1774296548000},"page":"8151-8163","source":"Crossref","is-referenced-by-count":0,"title":["A Circular Window-Based Cascade Transformer for Online Action Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8438-1351","authenticated-orcid":false,"given":"Shuqiang","family":"Cao","sequence":"first","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0754-6458","authenticated-orcid":false,"given":"Weixin","family":"Luo","sequence":"additional","affiliation":[{"name":"Meituan","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bairui","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University","place":["Jinan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3313258"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177942"},{"key":"ref6","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Huang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2859029"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3342697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"ref11","article-title":"LAP-Net: Adaptive features sampling via learning action progression for online action detection","author":"Qu","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref13","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00316"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650511"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00813"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref23","first-page":"1","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","volume-title":"Proc. ECCV THUMOS Workshop","author":"Karaman","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477701"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2884469"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.49"},{"key":"ref34","article-title":"Efficient U-transformer with boundary-aware loss for action segmentation","author":"Du","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16041-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00950"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01721"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01326"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01759"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref52","first-page":"344","article-title":"Gaussian temporal awareness networks for action localization","volume-title":"Proc. IEEE Conf. Proc.","author":"Fuchen","year":"2019"},{"key":"ref53","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3280737"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_26"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107954"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108741"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00803"},{"key":"ref65","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11450348.pdf?arnumber=11450348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:10:58Z","timestamp":1790709058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3676664","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}