Multimodal Sentiment Analysis On Cmu Mosi
评估指标
Acc-2
Acc-7
Corr
F1
MAE
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Acc-2 | Acc-7 | Corr | F1 | MAE |
|---|---|---|---|---|---|
| teasel-a-transformer-based-speech-prefixed | 87.5 | 47.52 | 0.836 | 85 | 0.64 |
| improving-multimodal-fusion-with-hierarchical | 82.54 | 45.79 | 0.795 | 82.68 | 0.712 |
| speech-text-dialog-pre-training-for-spoken | 87.5 | - | - | - | - |
| meltr-meta-loss-transformer-for-learning-to | 85.3 | - | 0.789 | 85.4 | 0.759 |
| transmodality-an-end2end-fusion-method-with | - | - | - | - | - |
| multi-modality-multi-loss-fusion-network | 90.35 | 52.72 | 0.8824 | 90.35 | 0.5573 |
| improving-multimodal-fusion-with-hierarchical | 84.14 | 46.65 | 0.8 | 84 | 0.7 |
| improving-multimodal-fusion-with-hierarchical | 82.37 | 43.62 | 0.781 | 82.5 | 0.727 |
| unimse-towards-unified-multimodal-sentiment | 86.9 | 48.68 | 0.809 | 86.42 | 0.691 |
| learning-language-guided-adaptive-hyper | - | 49.42 | 0.805 | - | 0.683 |
| 10000-times-accelerated-robust-subset | 87.35 | 50.58 | 0.813 | 87.48 | 0.678 |
| adversarial-multimodal-domain-transfer-for | 84.3 | - | - | 84.2 | 0.716 |