Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.08049 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912467166167040 |
|---|---|
| author | Li, Ao Xu, Longwei Ling, Chen Zhang, Jinghui Wang, Pengwei |
| author_facet | Li, Ao Xu, Longwei Ling, Chen Zhang, Jinghui Wang, Pengwei |
| contents | Sentiment and emotion understanding are essential to applications such as human-computer interaction and depression detection. While Multimodal Large Language Models (MLLMs) demonstrate robust general capabilities, they face considerable challenges in the field of affective computing, particularly in detecting subtle facial expressions and handling complex emotion-related tasks, such as emotion reason inference and understanding emotions in long-context scenarios. Furthermore, there is a lack of a unified MLLM that can effectively handle both sentiment and emotion-related tasks. To address these challenges, we explore multi-task training strategies for MLLMs in affective computing and introduce Emotion Universe (EmoVerse), an MLLM designed to handle a broad spectrum of sentiment and emotion-related tasks. In addition, EmoVerse is capable of deeply analyzing the underlying causes of emotional states. We also introduce the Affective Multitask (AMT) Dataset, which supports multimodal sentiment analysis, multimodal emotion recognition, facial expression recognition, emotion reason inference, and emotion cause-pair extraction tasks. Extensive experiments demonstrate that EmoVerse outperforms existing methods, achieving state-of-the-art results in sentiment and emotion-related tasks. The code is available at https://github.com/liaolea/EmoVerse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08049 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EmoVerse: Exploring Multimodal Large Language Models for Sentiment and Emotion Understanding Li, Ao Xu, Longwei Ling, Chen Zhang, Jinghui Wang, Pengwei Computation and Language Sentiment and emotion understanding are essential to applications such as human-computer interaction and depression detection. While Multimodal Large Language Models (MLLMs) demonstrate robust general capabilities, they face considerable challenges in the field of affective computing, particularly in detecting subtle facial expressions and handling complex emotion-related tasks, such as emotion reason inference and understanding emotions in long-context scenarios. Furthermore, there is a lack of a unified MLLM that can effectively handle both sentiment and emotion-related tasks. To address these challenges, we explore multi-task training strategies for MLLMs in affective computing and introduce Emotion Universe (EmoVerse), an MLLM designed to handle a broad spectrum of sentiment and emotion-related tasks. In addition, EmoVerse is capable of deeply analyzing the underlying causes of emotional states. We also introduce the Affective Multitask (AMT) Dataset, which supports multimodal sentiment analysis, multimodal emotion recognition, facial expression recognition, emotion reason inference, and emotion cause-pair extraction tasks. Extensive experiments demonstrate that EmoVerse outperforms existing methods, achieving state-of-the-art results in sentiment and emotion-related tasks. The code is available at https://github.com/liaolea/EmoVerse. |
| title | EmoVerse: Exploring Multimodal Large Language Models for Sentiment and Emotion Understanding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.08049 |