Training A Small Emotional Vision Language Model for Visual Art Comprehension

arXiv:2403.11150v1 Announce Type: new
Abstract: This paper develops small vision language models to understand visual art, which, given an art work, aims to identify its emotion category and explain this prediction with natural language. While small models are computationally efficient, their capacity is much limited compared with large models. To break this trade-off, this paper builds a small emotional vision language model (SEVLM) by emotion modeling and input-output feature alignment. On the one hand, based on valence-arousal-dominance (VAD) knowledge annotated …

abstract art arxiv capacity cs.cv emotion identify language language model language models large models natural natural language paper prediction small training type vision vision language model visual work