{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:28Z","timestamp":1778048368195,"version":"3.51.4"},"reference-count":70,"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\/wacv61042.2026.00136","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1334-1344","source":"Crossref","is-referenced-by-count":0,"title":["FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs"],"prefix":"10.1109","author":[{"given":"Carlos","family":"Plou","sequence":"first","affiliation":[{"name":"University of Zaragoza,DIIS-I3A,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cesar","family":"Borja","sequence":"additional","affiliation":[{"name":"University of Zaragoza,DIIS-I3A,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruben","family":"Martinez-Cantin","sequence":"additional","affiliation":[{"name":"University of Zaragoza,DIIS-I3A,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana C.","family":"Murillo","sequence":"additional","affiliation":[{"name":"University of Zaragoza,DIIS-I3A,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"LLaMA 3.2: Multilingual large language models","year":"2023"},{"key":"ref2","first-page":"1","article-title":"The claude 3 model family: Opus, sonnet, haiku","volume":"1","year":"2024","journal-title":"Claude-3 Model Card"},{"key":"ref3","article-title":"Infinibench: A comprehensive benchmark for large multimodal models in very long video understanding","author":"Ataallah","year":"2024"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00162"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1684"},{"key":"ref7","article-title":"CG-bench: Clue-grounded question answering benchmark for long video understanding","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Chen"},{"key":"ref8","article-title":"Longvila: Scaling long-context visual language models for long videos","author":"Chen","year":"2024"},{"issue":"5","key":"ref9","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023","volume":"3","author":"Chiang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_18"},{"key":"ref11","article-title":"Long story short: a summarize-then-search method for long video question answering","author":"Chung","year":"2023"},{"key":"ref12","article-title":"Gemini: A family of highly capable multimodal models","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/2987588.JSTOR:2987588"},{"key":"ref14","article-title":"Streaming video question-answering with in-context video kv-cache retrieval","volume-title":"ICLR","author":"Di"},{"key":"ref15","article-title":"Streaming video question-answering with in-context video kv-cache retrieval","author":"Di","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327284"},{"key":"ref17","article-title":"Towards event-oriented long video understanding","author":"Du","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref22","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref23","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref24","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref26","article-title":"Video-llava: Learning united visual representation by alignment before projection","author":"Lin","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","article-title":"Litcab: Lightweight language model calibration over short-and long-form responses","author":"Liu","year":"2023"},{"key":"ref30","article-title":"Video-xl-pro: Reconstructive token compression for extremely long video understanding","author":"Liu","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref34","article-title":"Relaxed softmax: Efficient confidence auto-calibration for safe pedestrian detection","volume-title":"NeurIPS 2018 Workshop ML-ITS","author":"Neumann"},{"key":"ref35","article-title":"Chatgpt","year":"2023","journal-title":"openai.com"},{"key":"ref36","article-title":"Gpt-4v: Multimodal large language model","year":"2023","journal-title":"openai.com"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.eacl-long.164"},{"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","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref40","article-title":"Understanding long videos with multimodal language models","author":"Ranasinghe","year":"2024"},{"key":"ref41","article-title":"Understanding long videos in one multimodal language model pass","volume-title":"Int. Conference on Learning Representations","author":"Ranasinghe"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref43","article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref46","article-title":"Eva-clip-18b: Scaling clip to 18 billion parameters","author":"Sun","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref48","article-title":"Is imagenet worth 1 video? learning strong image encoders from 1 long unlabelled video","author":"Venkataramanan","year":"2023"},{"key":"ref49","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02131"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref52","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"ref53","article-title":"Lifelongmemory: Leveraging llms for answering queries in long-form egocentric videos","author":"Wang","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"ref55","article-title":"Longvideobench: A benchmark for long-context interleaved video-language understanding","author":"Wu","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02385-8"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref61","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref65","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref68","article-title":"Videoagent2: Enhancing the llm-based agent system for long-form video understanding by uncertainty-aware cot","author":"Zhi","year":"2025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01278"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01760"}],"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\/11492755.pdf?arnumber=11492755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:00:07Z","timestamp":1778047207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00136","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}