Multimodal Sentiment Analysis On Cmu Mosei 1
评估指标
Accuracy
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 | Accuracy |
|---|---|
| marlin-masked-autoencoder-for-facial-video | 73.7 |
| gated-mechanism-for-attention-based | 81.14 |
| multilogue-net-a-context-aware-rnn-for-multi | 82.10 |
| marlin-masked-autoencoder-for-facial-video | 72.69 |
| multi-modality-multi-loss-fusion-network | 88.22 |
| multi-label-emotion-analysis-in-conversation | 88.62 |
| a-transformer-based-joint-encoding-for-1 | 82.48 |
| learning-language-guided-adaptive-hyper | - |
| multimodal-language-analysis-in-the-wild-cmu | 76.9 |
| unimse-towards-unified-multimodal-sentiment | 87.50 |
| speech-text-dialog-pre-training-for-spoken | 87.34 |
| mmlatch-bottom-up-top-down-fusion-for | 82.4 |
| marlin-masked-autoencoder-for-facial-video | 74.83 |
| modulated-fusion-using-transformer-for | 82.45 |
| unsupervised-multimodal-language | 78 |