{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:00:51Z","timestamp":1778248851604,"version":"3.51.4"},"reference-count":50,"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\/wacv61042.2026.00695","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7198-7207","source":"Crossref","is-referenced-by-count":1,"title":["MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding"],"prefix":"10.1109","author":[{"given":"Pengyi","family":"Li","sequence":"first","affiliation":[{"name":"AXXX,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Irina","family":"Abdullaeva","sequence":"additional","affiliation":[{"name":"AXXX,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Gambashidze","sequence":"additional","affiliation":[{"name":"AXXX,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"AXXX,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Oseledets","sequence":"additional","affiliation":[{"name":"AXXX,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","article-title":"Scaling video-language models to 10k frames via hierarchical differential distillation","author":"Cheng","year":"2025"},{"key":"ref7","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref8","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref12","article-title":"Omnifusion technical report","author":"Goncharova","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/9789812836021_0015"},{"key":"ref14","article-title":"Logic-in-frames: Dynamic keyframe search via visual semantic-logical verification for long video understanding","author":"Guo","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01279"},{"key":"ref16","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref18","article-title":"Video-lavit: Unified video-language pre-training with decoupled visual-motional tokenization","author":"Jin","year":"2024"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref21","first-page":"36","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2017.10.014"},{"key":"ref25","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.828772"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1889"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.51644\/9781771120920-031"},{"key":"ref34","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref35","first-page":"15","article-title":"Feature selection by maximum marginal diversity","author":"Vasconcelos","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.283"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00311"},{"key":"ref39","article-title":"Longvideobench: A benchmark for long-context interleaved video-language understanding","author":"Wu","year":"2024"},{"key":"ref40","article-title":"Vllms provide better context for emotion understanding through common sense reasoning","author":"Xenos","year":"2024"},{"key":"ref41","article-title":"Slowfast-llava: A strong training-free baseline for video large language models","author":"Xu","year":"2024"},{"key":"ref42","article-title":"Longvila: Scaling long-context visual language models for long videos","author":"Xue","year":"2024"},{"key":"ref43","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.921"},{"key":"ref45","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"ref46","article-title":"Frame-voyager: Learning to query frames for video large language models","author":"Yu","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref48","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02048"},{"key":"ref50","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024"}],"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\/11492694.pdf?arnumber=11492694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:08:35Z","timestamp":1778047715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00695","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}