{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:44Z","timestamp":1777890224986,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00107","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1068-1077","source":"Crossref","is-referenced-by-count":0,"title":["Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark"],"prefix":"10.1109","author":[{"given":"Changsheng","family":"Gao","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Media Interactive Computing Lab,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaoxi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yenan","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China,230093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Media Interactive Computing Lab,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Variational image compression with a scale hyperprior","author":"Ball\u00e9","year":"2018","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3200698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3679013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202501094"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"ref11","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_29"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3456549"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3130754"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/PCS60826.2024.10566361"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DCC58796.2024.00073"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3467124"},{"key":"ref19","article-title":"Challenges and applications of large language models","author":"Kaddour","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Bridging compressed image latents and multimodal large language models","author":"Kao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3302858"},{"key":"ref22","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Lee","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05779-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3608643"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2024.3434520"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094830"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441049"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3216981"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849908"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849862"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859894"},{"key":"ref33","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356548"},{"key":"ref36","article-title":"Eva-CLIP: improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107716"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3510033"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01252"},{"key":"ref40","article-title":"SMC++: masked learning of unsupervised video semantic compression","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_10"},{"key":"ref42","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Split learning for health: Distributed deep learning without sharing raw patient data","author":"Vepakomma","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3094300"},{"key":"ref45","first-page":"53366","article-title":"NExT-GPT: Any-to-any multimodal LLM","author":"Wu","year":"2024","journal-title":"ICML"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICMC60390.2024.00008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3121131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367293"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref50","article-title":"All-in-one image coding for joint human-machine vision with multipath aggregation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428258"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.303"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446124.pdf?arnumber=11446124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:32Z","timestamp":1777613612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00107","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}