{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:30Z","timestamp":1778048310632,"version":"3.51.4"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00035","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"276-286","source":"Crossref","is-referenced-by-count":0,"title":["Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?"],"prefix":"10.1109","author":[{"given":"Manuel","family":"Benavent-Lledo","sequence":"first","affiliation":[{"name":"Universidad de Alicante,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Bacharidis","sequence":"additional","affiliation":[{"name":"Foundation for Research and Technology-Hellas,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victoria","family":"Manousaki","sequence":"additional","affiliation":[{"name":"Foundation for Research and Technology-Hellas,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Papoutsakis","sequence":"additional","affiliation":[{"name":"Foundation for Research and Technology-Hellas,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonis","family":"Argyros","sequence":"additional","affiliation":[{"name":"Foundation for Research and Technology-Hellas,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Garcia-Rodriguez","sequence":"additional","affiliation":[{"name":"Universidad de Alicante,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14350-z"},{"key":"ref2","article-title":"V-jepa 2: Self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412033"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104560"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3169976"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref13","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00966"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44207-0_10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICEE63041.2024.10668316"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051842"},{"key":"ref24","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341160"},{"key":"ref26","article-title":"Human action anticipation: A survey","author":"Lai","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-03071-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976305"},{"key":"ref33","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00206"},{"key":"ref35","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_30"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103764"},{"key":"ref40","article-title":"Pedestrian action anticipation using contextual feature fusion in stacked rnns","volume-title":"BMVC","author":"Rasouli"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/AISP61396.2024.10475221"},{"key":"ref42","article-title":"Actioncomet: A zero-shot approach to learn image-specific commonsense concepts about actions","author":"Sampat","year":"2024"},{"key":"ref43","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3577925"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01242"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref53","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref54","first-page":"1086","article-title":"Long short-term transformer for online action detection","volume-title":"Advances in Neural Information Processing Systems","author":"Xu","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222914"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"ref58","article-title":"Antgpt: Can large language models help long-term action anticipation from videos","volume-title":"ICLR","author":"Zhao"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492292.pdf?arnumber=11492292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:55:53Z","timestamp":1778046953000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00035","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}