Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.19549 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912669406068736 |
|---|---|
| author | Li, Deng Xing, Bohao Liu, Xin Xia, Baiqiang Wen, Bihan Kälviäinen, Heikki |
| author_facet | Li, Deng Xing, Bohao Liu, Xin Xia, Baiqiang Wen, Bihan Kälviäinen, Heikki |
| contents | Emotion understanding is a critical yet challenging task. Most existing approaches rely heavily on identity-sensitive information, such as facial expressions and speech, which raises concerns about personal privacy. To address this, we introduce the De-identity Multimodal Emotion Recognition and Reasoning (DEEMO), a novel task designed to enable emotion understanding using de-identified video and audio inputs. The DEEMO dataset consists of two subsets: DEEMO-NFBL, which includes rich annotations of Non-Facial Body Language (NFBL), and DEEMO-MER, an instruction dataset for Multimodal Emotion Recognition and Reasoning using identity-free cues. This design supports emotion understanding without compromising identity privacy. In addition, we propose DEEMO-LLaMA, a Multimodal Large Language Model (MLLM) that integrates de-identified audio, video, and textual information to enhance both emotion recognition and reasoning. Extensive experiments show that DEEMO-LLaMA achieves state-of-the-art performance on both tasks, outperforming existing MLLMs by a significant margin, achieving 74.49% accuracy and 74.45% F1-score in de-identity emotion recognition, and 6.20 clue overlap and 7.66 label overlap in de-identity emotion reasoning. Our work contributes to ethical AI by advancing privacy-preserving emotion understanding and promoting responsible affective computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19549 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DEEMO: De-identity Multimodal Emotion Recognition and Reasoning Li, Deng Xing, Bohao Liu, Xin Xia, Baiqiang Wen, Bihan Kälviäinen, Heikki Computer Vision and Pattern Recognition Emotion understanding is a critical yet challenging task. Most existing approaches rely heavily on identity-sensitive information, such as facial expressions and speech, which raises concerns about personal privacy. To address this, we introduce the De-identity Multimodal Emotion Recognition and Reasoning (DEEMO), a novel task designed to enable emotion understanding using de-identified video and audio inputs. The DEEMO dataset consists of two subsets: DEEMO-NFBL, which includes rich annotations of Non-Facial Body Language (NFBL), and DEEMO-MER, an instruction dataset for Multimodal Emotion Recognition and Reasoning using identity-free cues. This design supports emotion understanding without compromising identity privacy. In addition, we propose DEEMO-LLaMA, a Multimodal Large Language Model (MLLM) that integrates de-identified audio, video, and textual information to enhance both emotion recognition and reasoning. Extensive experiments show that DEEMO-LLaMA achieves state-of-the-art performance on both tasks, outperforming existing MLLMs by a significant margin, achieving 74.49% accuracy and 74.45% F1-score in de-identity emotion recognition, and 6.20 clue overlap and 7.66 label overlap in de-identity emotion reasoning. Our work contributes to ethical AI by advancing privacy-preserving emotion understanding and promoting responsible affective computing. |
| title | DEEMO: De-identity Multimodal Emotion Recognition and Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19549 |