{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:54:43Z","timestamp":1777568083642,"version":"3.51.4"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445945","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"2765-2769","source":"Crossref","is-referenced-by-count":13,"title":["VGDIFFZERO: Text-To-Image Diffusion Models Can Be Zero-Shot Visual Grounders"],"prefix":"10.1109","author":[{"given":"Xuyang","family":"Liu","sequence":"first","affiliation":[{"name":"Sichuan University,College of Electronics and Information Engineering,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siteng","family":"Huang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yachen","family":"Kang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honggang","family":"Chen","sequence":"additional","affiliation":[{"name":"Sichuan University,College of Electronics and Information Engineering,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,School of Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446504"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53305-1_15"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref17","article-title":"Diffusion models for zero-shot open-vocabulary segmentation","author":"Karazija","year":"2023"},{"key":"ref18","article-title":"Discriminative diffusion models as few-shot vision and language learners","author":"He","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref20","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref21","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"NeurIPS","author":"Ren"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445945.pdf?arnumber=10445945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:59:17Z","timestamp":1722574757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445945","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}