EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment

TL;DR

This paper introduces EEmo-Logic, a multi-stage framework utilizing a large, comprehensive dataset for detailed image-evoked emotion understanding, advancing machine empathy and human-computer interaction.

Contribution

It presents EEmoDB, the largest dataset for emotion understanding, and EEmo-Logic, a multimodal large language model fine-tuned for emotion assessment and reasoning.

Findings

EEmo-Logic outperforms existing models in emotion QA tasks.

The dataset enables comprehensive emotion analysis across multiple dimensions.

EEmo-Logic demonstrates strong generalization in cross-domain evaluations.

Abstract

Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowering diverse human-computer interaction applications. However, existing models are still limited to coarse-grained emotion perception or deficient reasoning capabilities. To bridge this gap, we introduce EEmoDB, the largest image-evoked emotion understanding dataset to date. It features $5$ analysis dimensions spanning $5$ distinct task categories, facilitating comprehensive interpretation. Specifically, we compile $1.2M$ question-answering (QA) pairs (EEmoDB-QA) from $125k$ images via automated generation, alongside a $36k$ dataset (EEmoDB-Assess) curated from $25k$ images for fine-grained assessment. Furthermore, we propose EEmo-Logic, an all-in-one multimodal large language model (MLLM) developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design. Extensive experiments demonstrate that EEmo-Logic achieves robust performance in in-domain and cross-domain datasets, excelling in emotion QA and fine-grained assessment. The code is available at https://anonymous.4open.science/r/EEmoLogic.