MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning In Vision-Language Models
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (3) · 1882-1890
DOI: 10.1609/aaai.v40i3.37168 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von SangEun Lee und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Understanding human emotions from images is a challenging yet essential task for vision-language models. While recent efforts have fine-tuned vision-language models to enhance emotional awareness, most approaches rely on global visual representations and fail to capture the nuanced and multi-faceted nature of emotional cues. Furthermore, most existing approaches adopt instruction tuning, which requires costly dataset construction and involves training a large number of parameters, thereby limiting their scalability and efficiency. To address these challenges, we propose MASP, a novel framework for Multi-Aspect guided emotion reasoning with Soft Prompt tuning in vision-language models. MASP explicitly separates emotion-relevant visual cues via multi-aspect cross-attention modules and guides the language model using soft prompts, enabling efficient and scalable task adaptation without modifying the base model. Our method achieves state-of-the-art performance on various emotion recognition benchmarks, demonstrating that the explicit modeling of multi-aspect emotional cues with soft prompt tuning leads to more accurate and interpretable emotion reasoning in vision-language models.
Zitieren
APA
Lee, S., Lee, Y., Park, E., & Chae, W. (2026). MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning In Vision-Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(3), 1882-1890. https://doi.org/10.1609/aaai.v40i3.37168
Vancouver
Lee S, Lee Y, Park E, Chae W. MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning In Vision-Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(3):1882-1890. doi:10.1609/aaai.v40i3.37168
BibTeX
@article{Lee2026,
author = {Lee, SangEun and Lee, Yubeen and Park, Eunil and Chae, Wonseok},
title = {MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning In Vision-Language Models},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {3},
pages = {1882--1890},
doi = {10.1609/aaai.v40i3.37168}
}
EUVIMED