{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T08:09:58Z","timestamp":1772006998503,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1109\/vcip67698.2025.11396912","type":"proceedings-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:55:27Z","timestamp":1771966527000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["PITR-Select: Partial Image Token Reduction via Temporal Selection for Efficient Video Understanding on Edge"],"prefix":"10.1109","author":[{"given":"Fadoua","family":"Ghourabi","sequence":"first","affiliation":[{"name":"AWL, Inc.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kittinun","family":"Aukkapinyo","sequence":"additional","affiliation":[{"name":"AWL, Inc.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Fujimura","sequence":"additional","affiliation":[{"name":"AWL, Inc.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kriti","family":"Agarwal","sequence":"additional","affiliation":[{"name":"AWL, Inc.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wasu","family":"Wasusatein","sequence":"additional","affiliation":[{"name":"AWL, Inc.,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","first-page":"34 892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref4","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref5","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops65533.2025.00078"},{"key":"ref8","article-title":"ReVision: A dataset and baseline VLM for privacy-preserving task-oriented visual instruction rewriting","author":"Mishra","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00828"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8090233"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/ICIP55913.2025.11084348","article-title":"Grid-LOGAT: Grid based local and global area transcription for video question answering","author":"Chowdhury","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00898"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVCS.2018.8496473"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01841"},{"key":"ref17","article-title":"SmolVLM: Redefining small and efficient multimodal models","author":"Marafioti","year":"2025"},{"key":"ref18","first-page":"21 715","article-title":"A simple LLM framework for long-range video question-answering","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref21","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref22","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref24","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS)","author":"Wu"}],"event":{"name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","location":"Klagenfurt, Austria","start":{"date-parts":[[2025,12,1]]},"end":{"date-parts":[[2025,12,4]]}},"container-title":["2025 International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11396756\/11396790\/11396912.pdf?arnumber=11396912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:18:41Z","timestamp":1772003921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/vcip67698.2025.11396912","relation":{},"subject":[],"published":{"date-parts":[[2025,12,1]]}}}