{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:54:11Z","timestamp":1776783251945,"version":"3.51.2"},"reference-count":41,"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\/icassp49660.2025.10889829","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Emotion Reasoning for Image Multi-Emotion Prediction"],"prefix":"10.1109","author":[{"given":"Bingbing","family":"Wang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geng","family":"Tu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixin","family":"Bai","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,SIAT,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zeng","sequence":"additional","affiliation":[{"name":"The 30th Research Institute of China Electronics Technology Group Corporation,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114274"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2023.0140728"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3551626.3564950"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120641"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00926"},{"key":"ref7","article-title":"Improving multimodal datasets with image captioning","volume":"36","author":"Nguyen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100116"},{"key":"ref10","article-title":"Image-of-thought prompting for visual reasoning refinement in multimodal large language models","author":"Zhou","year":"2024"},{"key":"ref11","article-title":"Should we fear large language models? a structural analysis of the human reasoning system for elucidating llm capabilities and risks through the lens of heidegger\u2019s philosophy","author":"Zhang","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.640"},{"key":"ref13","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298687"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916866"},{"key":"ref16","article-title":"Socratis: Are large multimodal models emotionally aware?","author":"Deng","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00642"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.192"},{"key":"ref20","article-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models","author":"Shao","year":"2024"},{"key":"ref21","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502282"},{"key":"ref23","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2939744"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467339"},{"key":"ref27","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref28","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2971475"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v13i01.3225"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2501\/S0021849906060041"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2196\/30854"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.4018\/JGIM.319309"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.034"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-022-01000-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-023-01617-9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6755-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICICoS62600.2024.10636889"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"}],"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\/10889829.pdf?arnumber=10889829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:48Z","timestamp":1774416168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889829","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}