{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:58Z","timestamp":1777889218218,"version":"3.51.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/5011000037250","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2022R1A5A1027646"],"award-info":[{"award-number":["2022R1A5A1027646"]}],"id":[{"id":"10.13039\/5011000037250","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01059","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11383-11392","source":"Crossref","is-referenced-by-count":0,"title":["ContextFace: Generating Facial Expressions from Emotional Contexts"],"prefix":"10.1109","author":[{"given":"Min-jung","family":"Kim","sequence":"first","affiliation":[{"name":"Korea University LG Electronics,Dept. of Computer Science and Engineering,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsang","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University SK Telecom,Dept. of Computer Science and Engineering,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung Jun","family":"Baek","sequence":"additional","affiliation":[{"name":"Korea University,Dept. of Computer Science and Engineering,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","volume-title":"Anthropic. Claude-3.5-sonnet-20241022","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00440"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"ref7","volume-title":"Inferno.","author":"Dan\u011b\u010dek","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802538"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802538"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"ref14","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref15","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"ref17","author":"Lei","year":"2024","journal-title":"Large vision-language models as emotion recognizers in context awareness"},{"key":"ref18","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref20","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"ref23","article-title":"Explainable multimodal emotion reasoning","author":"Lian","year":"2023","journal-title":"CoRR"},{"key":"ref24","author":"Lian","year":"2024","journal-title":"Affectgpt: Dataset and framework for explainable multimodal emotion recognition"},{"key":"ref25","first-page":"26689","article-title":"Vila: On pre-training for vi-sual language models","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Lin","year":"2024"},{"key":"ref26","author":"Lin","year":"2024","journal-title":"Emoface: Emotion-content disentangled speech-driven 3d talking face with mesh attention"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref28","author":"Liu","year":"2023","journal-title":"LLaVA- Llama-2\u201313B-chat: Lightning Preview"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref31","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref32","first-page":"1","article-title":"A dualbranch adaptive distribution fusion framework for real-world facial expression recognition","volume-title":"ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Liu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01975"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00925"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/fg61629.2025.11099375"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-022-00867-0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3521321"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.532279"},{"key":"ref42","article-title":"Paligemma 2: A family of versatile vlms for transfer","author":"Steiner","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","year":"2025","journal-title":"Qwen Team. Qwen2.5-vl"},{"key":"ref44","author":"Wang","year":"2025","journal-title":"Qcs: Feature refining from quadruplet cross similarity for facial expression recognition"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn64981.2025.11227260"},{"key":"ref46","author":"Xing","year":"2024","journal-title":"Emo-llama: Enhancing facial emotion understanding with instruction tuning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107901"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445109.pdf?arnumber=11445109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:11Z","timestamp":1777612151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01059","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}