Emotional Video Captioning on EVC Combine
76.4AccswMM-ECPE++
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MM-ECPE++Language Decoder=FLAN-T5 XL, Visual Backbone=VideoBLIP2026.06 | 76.4 | 74.3 | 78.9 | 59.2 | 42.6 | 30.5 | 26.8 | 54.5 | 69 | 50.8 | 70.3 | |
| FACE-net2026.03 | 75.9 | 74.4 | 78.7 | 59.1 | 43.4 | 30.9 | 26.9 | 54 | 69.2 | 51.1 | 70.5 | |
| MM-ECPE2026.03 | 75.6 | 73.8 | 78.1 | 58.5 | 42.3 | 30.2 | 26.4 | 53.8 | 67.9 | 50.4 | 69.3 | |
| MM-ECPE2026.06 | 75.6 | 73.8 | 78.1 | 58.5 | 42.3 | 30.2 | 26.4 | 53.8 | 67.9 | 50.4 | 69.3 | |
| DCGN2026.03 | 74.8 | 73.1 | 75.6 | 56.7 | 40.5 | 28.5 | 24.9 | 51.7 | 49.8 | 48.5 | 51.7 | |
| DCGN2026.06 | 74.8 | 73.1 | 75.6 | 56.7 | 40.5 | 28.5 | 24.9 | 51.7 | 49.8 | 48.5 | 51.7 | |
| EPAN2026.03 | 69.3 | 67.2 | 74.4 | 55.6 | 39.9 | 28 | 23 | 47.1 | 43 | 47 | 48 | |
| EPAN2026.06 | 69.3 | 67.2 | 74.4 | 55.6 | 39.9 | 28 | 23 | 47.1 | 43 | 47 | 48 | |
| VEIN2026.03 | 59 | 57.6 | 72.1 | 52.8 | 37.9 | 27.1 | 21.6 | 46.8 | 39.4 | 43.6 | 43.1 | |
| VEIN2026.06 | 59 | 57.6 | 72.1 | 52.8 | 37.9 | 27.1 | 21.6 | 46.8 | 39.4 | 43.6 | 43.1 | |
| VideoBLIP2026.03 | 58.4 | 57.2 | 74.1 | 56 | 40.8 | 29.2 | 25.3 | 52 | 65.6 | 45.8 | 63.6 | |
| CANet2026.03 | 53.7 | 52.7 | 68.1 | 47.7 | 32.9 | 22.5 | 19.7 | 43.7 | 34.5 | 38.8 | 38.2 | |
| CANet2026.06 | 53.7 | 52.7 | 68.1 | 47.7 | 32.9 | 22.5 | 19.7 | 43.7 | 34.5 | 38.8 | 38.2 | |
| SA-LSTM2026.03 | 53.4 | 50.7 | 70.6 | 51.4 | 36.7 | 25.4 | 21 | 45.9 | 38.8 | 41.2 | 41.5 | |
| SA-LSTM2026.06 | 53.4 | 50.7 | 70.6 | 51.4 | 36.7 | 25.4 | 21 | 45.9 | 38.8 | 41.2 | 41.5 | |
| FT2026.03 | 51.2 | 49.6 | 67.6 | 47.2 | 32 | 21.6 | 20.4 | 43.1 | 29 | 37.6 | 33.3 | |
| FT2026.06 | 51.2 | 49.6 | 67.6 | 47.2 | 32 | 21.6 | 20.4 | 43.1 | 29 | 37.6 | 33.3 | |
| SGN2026.06 | 50.4 | 48.6 | 68.7 | 48.9 | 34.2 | 24 | 20.1 | 44.8 | 35.5 | 39.1 | 38.3 |