{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:56Z","timestamp":1778048396848,"version":"3.51.4"},"reference-count":62,"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\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","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\/wacv61042.2026.00030","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"225-235","source":"Crossref","is-referenced-by-count":0,"title":["TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors"],"prefix":"10.1109","author":[{"given":"Wei-Yuan","family":"Cheng","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai-Po","family":"Chang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Pin","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fu-En","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0900"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00832"},{"key":"ref6","article-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref9","article-title":"Violet: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref13","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref17","article-title":"Video-lavit: Unified video-language pre-training with decoupled visual-motional tokenization","author":"Jin","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00944"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref29","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Decoding-time realignment of language models","author":"Liu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00390"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref35","article-title":"Frozen transformers in language models are effective visual encoder layers","author":"Pang","year":"2023"},{"key":"ref36","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref39","article-title":"Longvu: Spa-tiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024"},{"key":"ref40","article-title":"Decoding-time language model alignment with multiple objectives","author":"Shi","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6881"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref44","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref47","article-title":"Learning grounded vision-language representation for versatile understanding in untrimmed videos","author":"Wang","year":"2023"},{"key":"ref48","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"ref49","article-title":"Timerefine: Temporal grounding with time refining video llm","author":"Wang","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref51","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01769"},{"key":"ref54","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024"},{"key":"ref55","article-title":"Longvila: Scaling long-context visual language models for long videos","author":"Xue","year":"2024"},{"key":"ref56","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref57","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024"},{"key":"ref58","author":"Zhang","year":"2024","journal-title":"Llava-next: A strong zero-shot video understanding model"},{"key":"ref59","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref62","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\/11492733.pdf?arnumber=11492733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:00:01Z","timestamp":1778047201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00030","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}