{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T13:51:28Z","timestamp":1779198688808,"version":"3.51.4"},"reference-count":52,"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\/iccv51701.2025.02127","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22911-22921","source":"Crossref","is-referenced-by-count":2,"title":["HERMES: Temporal-Coherent Long-form Understanding with Episodes and Semantics"],"prefix":"10.1109","author":[{"given":"Gueter Josmy","family":"Faure","sequence":"first","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Fong","family":"Yeh","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Hung","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Ting","family":"Su","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang-Hong","family":"Lai","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Winston H.","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8516.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2011.10.001"},{"key":"ref3","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00632"},{"issue":"3","key":"ref6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2004.08.028"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00334"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref13","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01798"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref19","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01721"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.102.3.419"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00176"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012375731-9\/50045-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref28","author":"Rae","year":"2019","journal-title":"Compressive transformers for longrange sequence modelling"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-7890-7_2"},{"key":"ref31","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems, 27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01661-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367879"},{"key":"ref37","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Elements of episodic memory","author":"Tulving","year":"1983","journal-title":"Oxford University Press"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.4135\/9781446212967.n15"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref45","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume":"34","author":"Xu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.133.2.273"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref51","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3366710"}],"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\/11445040.pdf?arnumber=11445040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:51Z","timestamp":1777613451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02127","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}