{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:55Z","timestamp":1782798295264,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571630","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understanding"],"prefix":"10.1109","author":[{"given":"Shengyuan","family":"Ye","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Qian","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liekang","family":"Zeng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Information Engineering,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mu","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Information Engineering,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowen","family":"Chu","sequence":"additional","affiliation":[{"name":"HKUST (Guangzhou),Data Science and Analytics Thrust,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijie","family":"Hong","sequence":"additional","affiliation":[{"name":"Shenzhen Smart City Communications Co., Ltd.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref2","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"ref4","article-title":"Vision-language model for object detection and segmentation: A review and evaluation","author":"Feng","year":"2025"},{"key":"ref5","article-title":"Openai api","year":"2025"},{"key":"ref6","article-title":"Personal llm agents: Insights and survey about the capability, efficiency and security","author":"Li","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044734"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-75091-5_17"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681022"},{"key":"ref10","first-page":"269","article-title":"Focus: Querying large video datasets with low latency and low cost","author":"Hsieh","year":"2018","journal-title":"OSDI 18"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388948"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01761"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00316"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00315"},{"key":"ref15","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref16","article-title":"Video-rag: Visually-aligned retrieval-augmented long video comprehension","author":"Luo","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621399"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3458305.3463377"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621148"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.162"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.25300\/misq\/2024\/17115"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.935"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00228"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref31","article-title":"Outdoor Full-Color Wired Dome Camera","year":"2014"},{"key":"ref32","article-title":"Jetson orin","year":"2025"},{"key":"ref33","article-title":"Jetson xavier nx","year":"2025"},{"key":"ref34","article-title":"Jetson tx2","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972764.29"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2002.994785"},{"key":"ref37","article-title":"Easyocr: Ready-to-use ocr with 80+ languages supported","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref41","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"ref43","first-page":"251","article-title":"Goldfish: Vision-language understanding of arbitrarily long videos","volume-title":"European Conference on Computer Vision","author":"Ataallah"},{"key":"ref44","first-page":"1","article-title":"Retrieval-augmented generation for large language models: A survey","volume":"2","author":"Gao","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01764"},{"key":"ref46","article-title":"Videorag: Retrieval-augmented generation with extreme long-context videos","author":"Ren","year":"2025"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571630.pdf?arnumber=11571630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:15:53Z","timestamp":1782796553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571630","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}