{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T06:11:04Z","timestamp":1781763064521,"version":"3.54.5"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687472","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Multi-modal Learnable Queries for Image Aesthetics Assessment"],"prefix":"10.1109","author":[{"given":"Zhiwei","family":"Xiong","sequence":"first","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqi","family":"Shen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiran","family":"Ren","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/118"},{"key":"ref2","author":"Xu","year":"2023","journal-title":"Imagereward: Learning and evaluating human preferences for text-toimage generation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967223"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 2021 International Conference on Machine Learning (ICML\u201921)","author":"Radford"},{"key":"ref10","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447746"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00422"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272984"},{"key":"ref20","author":"Hendrycks","year":"2016","journal-title":"Gaussian error linear units (gelus)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01412"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3308852"},{"key":"ref24","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687472.pdf?arnumber=10687472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:23:42Z","timestamp":1736969022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687472","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}