{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:19:14Z","timestamp":1761895154516,"version":"build-2065373602"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210205","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Grained Alignment for Visual Grounding"],"prefix":"10.1109","author":[{"given":"Hongbing","family":"Li","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinran","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.104"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"journal-title":"CVPR 2018","article-title":"Yolov3: An incremental improvement","author":"Farhadi","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"journal-title":"ICML 2021","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","key":"ref19"},{"journal-title":"ICML 2021","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","key":"ref20"},{"journal-title":"ICLR 2022","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"journal-title":"ICML 2021","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"journal-title":"ICML 2022","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"journal-title":"NeurIPS 2021","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00568"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210205.pdf?arnumber=11210205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:44:34Z","timestamp":1761889474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210205","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}