{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:32:13Z","timestamp":1778081533154,"version":"3.51.4"},"reference-count":40,"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\/wacv61042.2026.00217","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2188-2197","source":"Crossref","is-referenced-by-count":2,"title":["Beyond the Highlights: Video Retrieval with Salient and Surrounding Contexts"],"prefix":"10.1109","author":[{"given":"Jaehun","family":"Bang","sequence":"first","affiliation":[{"name":"UNIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moon","family":"Ye-Bin","sequence":"additional","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungdon","family":"Joo","sequence":"additional","affiliation":[{"name":"UNIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref4","article-title":"A short note about kinetics600","author":"Carreira","year":"2018"},{"key":"ref5","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019"},{"key":"ref6","article-title":"Pyscenedetect","author":"Castellano","year":"2024"},{"key":"ref7","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"Chen","year":"2011","journal-title":"Association for Computational Linguistics"},{"key":"ref8","article-title":"Valor: Vision-audio-language omni-perception pretraining model and dataset","author":"Chen","year":"2023"},{"key":"ref9","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref10","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00478"},{"key":"ref12","article-title":"Gramian multimodal representation learning and alignment","author":"Cicchetti","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref16","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00122"},{"key":"ref18","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref21","article-title":"Revisiting the role of language priors in vision-language models","author":"Lin","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref23","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"issue":"6","key":"ref26","first-page":"7","article-title":"Alpaca: A strong, replicable instructionfollowing model","volume":"3","author":"Taori","year":"2023","journal-title":"Stanford Center for Research on Foundation Models."},{"key":"ref27","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref28","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref30","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.156"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_14"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref35","article-title":"mplug-2: A modularized multi-modal foundation model across text, image and video","volume-title":"International Conference on Machine Learning (ICML)","author":"Xu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref37","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref39","article-title":"Selfcorrecting decoding with generative feedback for mitigating hallucinations in large vision-language models","author":"Zhang","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"}],"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\/11492288.pdf?arnumber=11492288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:55:51Z","timestamp":1778046951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00217","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}