Video Captioning on VALOR 32K
62.8CIDErMiCo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MiCo2024.06 | 62.8 | — | |
| VAST(1.3B)Sample=442M, Audio or subtitle modalities=true2023.05 | 62.2 | 9.9 | |
| VASTmodality track=Multi-modal2023.05 | 62 | — | |
| Method [7]modality track=Multi-modal2023.05 | 61.5 | — | |
| VALOR-LSample=433.5M, Audio or subtitle modalities=true2023.05 | 61.5 | 9.6 | |
| SOTA2024.06 | 61.5 | — | |
| SMPFFSample=None, Audio or subtitle modalities=true2023.05 | 37.1 | 7.5 | |
| Method [61]modality track=Vision-only2023.05 | 27.3 | — | |
| SwinBERTSample=None, Audio or subtitle modalities=false2023.05 | 27.3 | 5.4 |