Emotional Video Captioning on EVC-MSVD
91.3Accuracy (SW)FACE-net
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FACE-net2026.03 | 91.3 | 89.6 | 97.5 | 88.2 | 80.5 | 71.5 | 46.1 | 83.7 | 169.4 | 82.2 | 153.6 | |
| MM-ECPE++Language Decoder=FLAN-T5 XL, Visual Backbone=VideoBLIP2026.06 | 91.2 | 89.7 | 97.7 | 88.4 | 80.5 | 71.5 | 45.8 | 83.8 | 169.6 | 82.3 | 153.8 | |
| MM-ECPE2026.03 | 90.4 | 89.1 | 96.9 | 87.8 | 80.2 | 71.4 | 45.5 | 83.1 | 168.3 | 81.8 | 152.6 | |
| MM-ECPE2026.06 | 90.4 | 89.1 | 96.9 | 87.8 | 80.2 | 71.4 | 45.5 | 83.1 | 168.3 | 81.8 | 152.6 | |
| DCGN2026.03 | 86.5 | 85.7 | 84.5 | 70.9 | 59.2 | 48.7 | 35.7 | 71 | 85.2 | 65.7 | 86.6 | |
| DCGN2026.06 | 86.5 | 85.7 | 84.5 | 70.9 | 59.2 | 48.7 | 35.7 | 71 | 85.2 | 65.7 | 86.6 | |
| VideoBLIP2026.03 | 85.7 | 84.7 | 94.1 | 85.7 | 77.5 | 69.7 | 43.4 | 81.6 | 159.4 | 78.8 | 142.6 | |
| EPAN2026.03 | 84.1 | 82.8 | 82.5 | 69.6 | 57.8 | 46.2 | 34.4 | 69.8 | 80.6 | 63.1 | 81.1 | |
| EPAN2026.06 | 84.1 | 82.8 | 82.5 | 69.6 | 57.8 | 46.2 | 34.4 | 69.8 | 80.6 | 63.1 | 81.1 | |
| VEIN2026.03 | 82.7 | 82.1 | 82 | 68.4 | 57.1 | 45.9 | 33 | 69 | 79.6 | 62.4 | 80.2 | |
| VEIN2026.06 | 82.7 | 82.1 | 82 | 68.4 | 57.1 | 45.9 | 33 | 69 | 79.6 | 62.4 | 80.2 | |
| CANet2026.03 | 78.7 | 76.8 | 78.5 | 64 | 52.1 | 41.8 | 30.8 | 65.7 | 74.4 | 57.9 | 75.1 | |
| CANet2026.06 | 78.7 | 76.8 | 78.5 | 64 | 52.1 | 41.8 | 30.8 | 65.7 | 74.4 | 57.9 | 75.1 | |
| SGN2026.06 | 73.9 | 73.1 | 77.5 | 62.7 | 51.3 | 41.1 | 30.6 | 63.6 | 71 | 56.4 | 71.5 | |
| FT2026.03 | 69.4 | 67.1 | 77.2 | 60.3 | 47.4 | 36.3 | 29 | 63.4 | 62.5 | 52.5 | 63.7 | |
| FT2026.06 | 69.4 | 67.1 | 77.2 | 60.3 | 47.4 | 36.3 | 29 | 63.4 | 62.5 | 52.5 | 63.7 | |
| SA-LSTM2026.03 | 68.8 | 67.2 | 80.7 | 67.9 | 56.3 | 45.5 | 33 | 68.2 | 72.1 | 59 | 71.3 | |
| SA-LSTM2026.06 | 68.8 | 67.2 | 80.7 | 67.9 | 56.3 | 45.5 | 33 | 68.2 | 72.1 | 59 | 71.3 |