{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:46:53Z","timestamp":1780634813095,"version":"3.54.1"},"reference-count":50,"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\/ijcnn64981.2025.11227260","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":6,"title":["VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Xenos","sequence":"first","affiliation":[{"name":"Queen Mary University of London,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niki M.","family":"Foteinopoulou","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioanna","family":"Ntinou","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioannis","family":"Patras","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Tzimiropoulos","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7463091"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0963721411422522"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.703"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2300000066"},{"key":"ref6","article-title":"Instructblip: Towards general-purpose visionlanguage models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00038"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1167\/7.1.10"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_52"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048693"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/spc3.12393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3091169"},{"key":"ref15","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/UPCON50219.2020.9376440"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"ref19","article-title":"Instructerc: Reforming emotion recognition in conversation with a retrieval multitask llms framework","author":"Lei","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icme57554.2024.10687508"},{"key":"ref21","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3064918"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB52358.2021.9484370"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref25","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","author":"Liu","year":"2019","journal-title":"Roberta: A robustly optimized bert pretraining approach"},{"key":"ref27","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01215-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01424"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666957"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102855"},{"key":"ref33","article-title":"Llava finds free lunch: Teaching human behavior improves content understanding abilities of llms","author":"Singh","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.108637"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"ref36","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3507000"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547755"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01183"},{"key":"ref44","article-title":"Emollm: Multimodal emotional understanding meets large language models","author":"Yang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00034"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.257"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01821"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107901"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref50","article-title":"Prompting visual-language models for dynamic facial expression recognition","volume-title":"British Machine Vision Conference (BMVC)","author":"Zhao"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227260.pdf?arnumber=11227260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:00Z","timestamp":1763191500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227260","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}