{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:21Z","timestamp":1777865301693,"version":"3.51.4"},"reference-count":55,"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\/iccv51701.2025.00975","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10475-10484","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Group Detection using VLM-augmented Temporal Groupness Graph"],"prefix":"10.1109","author":[{"given":"Kaname","family":"Yokoyama","sequence":"first","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chihiro","family":"Nakatani","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norimichi","family":"Ukita","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Conducting interaction: patterns of behavior in focused encounters","author":"Adam","year":"1990"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329302"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247888"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_28"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.70.066111"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589859"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/p10008"},{"key":"ref11","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_40"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0123783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.176"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_15"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070525"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342121"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_14"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11208"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3392824"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2013.6636640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/MVA51890.2021.9511390"},{"key":"ref28","article-title":"On spectral clustering: Analysis and an algorithm","author":"Ng","year":"2001","journal-title":"NIPS"},{"key":"ref29","article-title":"Dinov2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_33"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6247899"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738732"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2470658"},{"key":"ref35","article-title":"Conversational group detection with deep convolutional networks","author":"Swofford","year":"2018","journal-title":"CoRR, abs\/1810.04039"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556611"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479963"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.06.011"},{"key":"ref40","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_35"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.05.020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995468"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_35"},{"key":"ref49","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3324868"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01513-4"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_61"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381040"},{"key":"ref54","article-title":"Learning from labeled and unlabeled data with label propagation","author":"Zhu","year":"2002","journal-title":"Technical report, CMU-CALD-02\u2013107"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"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\/11445081.pdf?arnumber=11445081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:29Z","timestamp":1777529609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00975","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}