📊 Showing 8 results | 📏 Metric: BLEU-4
| Rank | Model | Paper | BLEU-4 | Date | Code |
|---|---|---|---|---|---|
| 1 | VALOR 📚 | VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset | 45.60 | 2023-04-17 | 📦 TXH-mercury/VALOR |
| 2 | VAST 📚 | VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset | 45.00 | 2023-05-29 | 📦 TXH-mercury/VALOR 📦 txh-mercury/vast |
| 3 | COSA 📚 | COSA: Concatenated Sample Pretrained Vision-Language Foundation Model | 43.70 | 2023-06-15 | 📦 txh-mercury/cosa |
| 4 | VideoCoCa 📚 | VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners | 39.70 | 2022-12-09 | - |
| 5 | VASTA (Kinetics-backbone) | Diverse Video Captioning by Adaptive Spatio-temporal Attention | 36.25 | 2022-08-19 | 📦 zohrehghaderi/vasta |
| 6 | CoCap (ViT/L14) | Accurate and Fast Compressed Video Captioning | 35.80 | 2023-09-22 | 📦 acherstyx/CoCap |
| 7 | ORG-TRL 📚 | Object Relational Graph with Teacher-Recommended Learning for Video Captioning | 32.10 | 2020-02-26 | - |
| 8 | NITS-VC | NITS-VC System for VATEX Video Captioning Challenge 2020 | 20.00 | 2020-06-07 | - |