{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T08:14:42Z","timestamp":1772007282279,"version":"3.50.1"},"reference-count":33,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/vcip67698.2025.11396859","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":["Dual-Layer Image Codec with Text Guidance for Hybrid Visual Perception"],"prefix":"10.1109","author":[{"given":"Tianma","family":"Shen","sequence":"first","affiliation":[{"name":"Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Quan","sequence":"additional","affiliation":[{"name":"Canyon Crest Academy,San Diego,CA,USA,92130"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3348995"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190860"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00100"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018075"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/PCS60826.2024.10566424"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441049"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02136"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.dte.2024.100013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3380458"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262251"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3261668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356548"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02129"},{"key":"ref18","article-title":"Prompt-icm: A unified framework towards image coding for machines with task-driven prompts","author":"Feng","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10648120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3150417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2023.3235058"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102750"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3525664"},{"key":"ref25","article-title":"Neural image compression with text-guided encoding for both pixel-level and perceptual fidelity","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref26","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"The Twelfth International Conference on Learning Representations","author":"Careil"},{"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","doi-asserted-by":"publisher","DOI":"10.1117\/12.2656516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref31","article-title":"BPG image format","author":"Bellard"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01697"}],"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\/11396859.pdf?arnumber=11396859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:27:20Z","timestamp":1772004440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/vcip67698.2025.11396859","relation":{},"subject":[],"published":{"date-parts":[[2025,12,1]]}}}