AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908821427847168 |
|---|---|
| author | Lian, Zheng Zhang, Fan Zhang, Yazhou Tao, Jianhua Liu, Rui Chen, Haoyu Li, Xiaobai He, Bin |
| author_facet | Lian, Zheng Zhang, Fan Zhang, Yazhou Tao, Jianhua Liu, Rui Chen, Haoyu Li, Xiaobai He, Bin |
| contents | Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by label spaces, enabling fine-grained emotion understanding. Unlike traditional discriminative methods, OV-MER leverages generative models to capture the full spectrum of emotions and employs emotion wheels (EWs) for metric calculation. Previous approaches (e.g., AffectGPT) primarily rely on token-level loss during training. However, this objective is misaligned with the metrics used in OV-MER, while these metrics cannot be optimized via gradient backpropagation. To address this limitation, we propose AffectGPT-R1, a reinforcement learning framework that treats EW-based metrics as a reward function and applies policy optimization to maximize this reward. Additionally, we introduce an explicit reasoning process and examine its necessity in OV-MER. To further guide model behavior, we incorporate auxiliary rewards that regularize both emotion reasoning and emotion prediction. We also apply length penalties to mitigate reward hacking. Experimental results demonstrate that AffectGPT-R1 yields significant performance improvements on OV-MER. Moreover, our approach enhances generalized emotion understanding, achieving state-of-the-art results on MER-UniBench. Our code is provided in the supplementary material and will be released to facilitate future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01318 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition Lian, Zheng Zhang, Fan Zhang, Yazhou Tao, Jianhua Liu, Rui Chen, Haoyu Li, Xiaobai He, Bin Human-Computer Interaction Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by label spaces, enabling fine-grained emotion understanding. Unlike traditional discriminative methods, OV-MER leverages generative models to capture the full spectrum of emotions and employs emotion wheels (EWs) for metric calculation. Previous approaches (e.g., AffectGPT) primarily rely on token-level loss during training. However, this objective is misaligned with the metrics used in OV-MER, while these metrics cannot be optimized via gradient backpropagation. To address this limitation, we propose AffectGPT-R1, a reinforcement learning framework that treats EW-based metrics as a reward function and applies policy optimization to maximize this reward. Additionally, we introduce an explicit reasoning process and examine its necessity in OV-MER. To further guide model behavior, we incorporate auxiliary rewards that regularize both emotion reasoning and emotion prediction. We also apply length penalties to mitigate reward hacking. Experimental results demonstrate that AffectGPT-R1 yields significant performance improvements on OV-MER. Moreover, our approach enhances generalized emotion understanding, achieving state-of-the-art results on MER-UniBench. Our code is provided in the supplementary material and will be released to facilitate future research. |
| title | AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2508.01318 |