{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:59Z","timestamp":1774419659538,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889954","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["SentiFormer: Metadata Enhanced Transformer for Image Sentiment Analysis"],"prefix":"10.1109","author":[{"given":"Bin","family":"Feng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shulan","family":"Ruan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzheng","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxuan","family":"Han","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijie","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-024-00326-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103166"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393384"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654930"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472195"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414150"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00791"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10033-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116256"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.062"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102855"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-024-02166-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570437"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref18","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref20","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref22","first-page":"29 441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"International Conference on Machine Learning","author":"Ryali"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10485"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873965"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3582649.3582678"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3118208"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20497-5_31"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10212-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93046-2_47"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02472-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16081-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680781"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111429"},{"issue":"11","key":"ref39","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2019.2939744"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2803520"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-020-00656-7"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889954.pdf?arnumber=10889954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:59Z","timestamp":1774416239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889954","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}