EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913171606863872 |
|---|---|
| author | Gao, Lancheng Jia, Ziheng Xing, Zixuan Sun, Wei Duan, Huiyu Zhai, Guangtao Min, Xiongkuo |
| author_facet | Gao, Lancheng Jia, Ziheng Xing, Zixuan Sun, Wei Duan, Huiyu Zhai, Guangtao Min, Xiongkuo |
| contents | 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 \textbf{EEmoDB}, the largest image-{\ul e}voked {\ul emo}tion understanding {\ul d}ataset 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 \textbf{EEmo-Logic}, an \textbf{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 dataset and code are available at https://github.com/workerred/EEmo-Logic. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01173 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment Gao, Lancheng Jia, Ziheng Xing, Zixuan Sun, Wei Duan, Huiyu Zhai, Guangtao Min, Xiongkuo Computer Vision and Pattern Recognition 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 \textbf{EEmoDB}, the largest image-{\ul e}voked {\ul emo}tion understanding {\ul d}ataset 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 \textbf{EEmo-Logic}, an \textbf{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 dataset and code are available at https://github.com/workerred/EEmo-Logic. |
| title | EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.01173 |