{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:03Z","timestamp":1778048463046,"version":"3.51.4"},"reference-count":91,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00492","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"5067-5078","source":"Crossref","is-referenced-by-count":0,"title":["TimeRefine: Temporal Grounding with Time Refining Video LLM"],"prefix":"10.1109","author":[{"given":"Xizi","family":"Wang","sequence":"first","affiliation":[{"name":"Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Cheng","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Wang","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Mohaiminul","family":"Islam","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorenzo","family":"Torresani","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gedas","family":"Bertasius","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Crandall","sequence":"additional","affiliation":[{"name":"Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref2","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.512"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref8","article-title":"Look closer to ground better: Weakly-supervised temporal grounding of sentence in video","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_23"},{"issue":"240","key":"ref12","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref17","article-title":"Excl: Extractive clip localization using natural language descriptions","author":"Ghosh","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref19","article-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref21","article-title":"Trace: Temporal grounding video llm via causal event modeling","author":"Guo","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref28","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20060"},{"key":"ref40","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.517"},{"key":"ref42","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref44","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.743"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref48","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref51","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref52","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref60","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.50"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01747"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref66","article-title":"Hawkeye: Training video-text llms for grounding text in videos","author":"Wang","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00311"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01789"},{"key":"ref69","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref70","article-title":"Star: A benchmark for situated reasoning in real-world videos","author":"Wu","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref73","article-title":"When, where, and what? a new dataset for anomaly detection in driving videos","author":"Yao","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02208"},{"key":"ref78","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022"},{"key":"ref79","article-title":"Timesuite: Improving mllms for long video understanding via grounded tuning","author":"Zeng","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_17"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_2"},{"key":"ref89","first-page":"42403","article-title":"Outline, then details: Syntactically guided coarse-to-fine code generation","volume-title":"International Conference on Machine Learning","author":"Zheng"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref91","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"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\/11492016.pdf?arnumber=11492016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:04:03Z","timestamp":1778047443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00492","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}