{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:48Z","timestamp":1781761908008,"version":"3.54.5"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"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":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11557050","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Temporal Action Localization Through Textual Guidance"],"prefix":"10.1109","author":[{"given":"Benedetta","family":"Liberatori","sequence":"first","affiliation":[{"name":"University of Trento,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Conti","sequence":"additional","affiliation":[{"name":"University of Trento,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Vaquero","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Rota","sequence":"additional","affiliation":[{"name":"University of Trento,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref5","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Open-vocabulary temporal action localization using multimodal guidance","author":"Gupta","year":"2024","journal-title":"BMVC"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01355"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00911"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01417"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00027"},{"key":"ref14","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.398"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3395778"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3395778"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01771"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02198"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref24","article-title":"Swapprompt: Test-time prompt adaptation for vision-language models","author":"Ma","year":"2023","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","author":"Manli","year":"2022","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref28","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00689"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref31","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3525"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref35","article-title":"Navero: Unlocking fine-grained semantics for video-language compositionality","author":"Tao","year":"2024","journal-title":"arXiv"},{"key":"ref36","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv"},{"key":"ref37","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"Wang","year":"2021","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref39","article-title":"Paxion: Patching action knowledge in video-language foundation models","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02524"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref42","article-title":"VideoCLIP: Contrastive pretraining for zero-shot video-text understanding","author":"Xu","year":"2021","journal-title":"EMNLP"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00012"},{"key":"ref46","article-title":"Temporal coherent test time optimization for robust video classification","author":"Yi","year":"2023","journal-title":"ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref49","article-title":"Memo: Test time robustness via adaptation and augmentation","author":"Zhang","year":"2022","journal-title":"NeurIPS"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11557050.pdf?arnumber=11557050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:59:53Z","timestamp":1781758793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11557050","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}