Visual Prompting in LLMs for Enhancing Emotion Recognition

TL;DR

This paper introduces a novel visual prompting method called Set-of-Vision (SoV) that enhances emotion recognition in vision large language models by utilizing spatial cues like bounding boxes and landmarks, leading to improved accuracy.

Contribution

The paper proposes the SoV approach that incorporates spatial visual prompts into VLLMs, addressing limitations in spatial localization and global context understanding for emotion recognition.

Findings

SoV improves face count accuracy.

SoV enhances emotion categorization performance.

Spatial prompts significantly boost model understanding of facial expressions.

Abstract

Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. To address this problem, we propose a Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through a battery of experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model's ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance.