VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning

arXiv:2404.07078v1 Announce Type: new
Abstract: Recognising emotions in context involves identifying the apparent emotions of an individual, taking into account contextual cues from the surrounding scene. Previous approaches to this task have involved the design of explicit scene-encoding architectures or the incorporation of external scene-related information, such as captions. However, these methods often utilise limited contextual information or rely on intricate training pipelines. In this work, we leverage the groundbreaking capabilities of Vision-and-Large-Language Models (VLLMs) to enhance in-context emotion classification …

arxiv common sense context cs.cv cs.hc emotion reasoning sense through type understanding