Emotional Video Captioning on EVC-VE
74.1AccswMM-ECPE++
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MM-ECPE++Language Decoder=FLAN-T5 XL, Visual Backbone=VideoBLIP2026.06 | 74.1 | 72.9 | 77.8 | 58.2 | 42.2 | 29.2 | 25.1 | 50.4 | 66.1 | 49.7 | 67.6 | |
| FACE-net2026.03 | 73.9 | 72.6 | 77.5 | 58.1 | 42.2 | 29.3 | 24.5 | 49.7 | 66.4 | 49.7 | 67.8 | |
| MM-ECPE2026.03 | 73.4 | 72.3 | 76.8 | 57.5 | 41.7 | 28.9 | 24.7 | 49.5 | 65.2 | 49.2 | 66.7 | |
| MM-ECPE2026.06 | 73.4 | 72.3 | 76.8 | 57.5 | 41.7 | 28.9 | 24.7 | 49.5 | 65.2 | 49.2 | 66.7 | |
| DCGN2026.03 | 71 | 69.4 | 74.5 | 55.3 | 40 | 28.1 | 23.4 | 47.7 | 41.5 | 47.3 | 46.9 | |
| DCGN2026.06 | 71 | 69.4 | 74.5 | 55.3 | 40 | 28.1 | 23.4 | 47.7 | 41.5 | 47.3 | 46.9 | |
| EPAN2026.03 | 63.8 | 62.3 | 73.6 | 54 | 38.3 | 27 | 21.2 | 42.3 | 34.7 | 45 | 40.4 | |
| EPAN2026.06 | 63.8 | 62.3 | 73.6 | 54 | 38.3 | 27 | 21.2 | 42.3 | 34.7 | 45 | 40.4 | |
| VideoBLIP2026.03 | 59.6 | 58.8 | 74.4 | 55.3 | 39.7 | 27.4 | 22.8 | 48.2 | 61.2 | 46.8 | 60.9 | |
| VEIN2026.03 | 57.4 | 56.8 | 71.6 | 52.1 | 37.4 | 26.3 | 20.9 | 41.7 | 33.4 | 43 | 39.2 | |
| VEIN2026.06 | 57.4 | 56.8 | 71.6 | 52.1 | 37.4 | 26.3 | 20.9 | 41.7 | 33.4 | 43 | 39.2 | |
| SA-LSTM2026.03 | 48.6 | 47.1 | 71 | 51.1 | 34.5 | 22.5 | 19.6 | 40.7 | 30.2 | 38.9 | 33.7 | |
| SA-LSTM2026.06 | 48.6 | 47.1 | 71 | 51.1 | 34.5 | 22.5 | 19.6 | 40.7 | 30.2 | 38.9 | 33.7 | |
| CANet2026.03 | 41.9 | 39.7 | 66.9 | 44.8 | 29.3 | 19.3 | 18.2 | 37.9 | 23.3 | 33.9 | 26.8 | |
| CANet2026.06 | 41.9 | 39.7 | 66.9 | 44.8 | 29.3 | 19.3 | 18.2 | 37.9 | 23.3 | 33.9 | 26.8 |