{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:29:26Z","timestamp":1761895766372,"version":"build-2065373602"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209055","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding"],"prefix":"10.1109","author":[{"given":"Jo\u00e3o","family":"Pereira","sequence":"first","affiliation":[{"name":"NOVA@FCT,NOVA LINCS,Caparica,Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasco","family":"Lopes","sequence":"additional","affiliation":[{"name":"DeepNeuronic,Covilhã,Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Semedo","sequence":"additional","affiliation":[{"name":"NOVA@FCT,NOVA LINCS,Caparica,Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o","family":"Neves","sequence":"additional","affiliation":[{"name":"University of Beira Interior,NOVA LINCS,Covilhã,Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"article-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref2"},{"article-title":"Video instruction tuning with synthetic data","year":"2024","author":"Zhang","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","year":"2024","author":"Wang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","year":"2024","author":"Shen","key":"ref10"},{"article-title":"Oryx mllm: On-demand spatial-temporal understanding at arbitrary resolution","year":"2024","author":"Liu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02436"},{"key":"ref13","article-title":"Self-RAG: Learning to retrieve, generate, and critique through self-reflection","author":"Asai","year":"2024","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref15","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref16","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","year":"2022","author":"Dao","key":"ref18"},{"article-title":"Mlvu: A comprehensive benchmark for multi-task long video understanding","year":"2024","author":"Zhou","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"year":"2024","key":"ref21","article-title":"Gpt-4o"},{"year":"2024","key":"ref22","article-title":"Gpt-4o mini"},{"article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","year":"2024","author":"Cheng","key":"ref23"},{"article-title":"Llava-onevision: Easy visual task transfer","year":"2024","author":"Li","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.866"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209055.pdf?arnumber=11209055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:58:07Z","timestamp":1761890287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209055","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}