| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Compression | 1920 x 1080 videos | Decoding Speed (fps)112.8 | 24 | |
| Video Coding | 1280 x 720 videos (test) | Encoding Speed (fps)225.1 | 16 | |
| Video Compression | 1080p videos | Encoding Latency (s)0.643 | 14 | |
| Neural Video Coding | 3840 x 2160 videos (test) | Encoding Speed (fps)35.5 | 12 | |
| Video Decoding | Videos | FPS395.9 | 12 | |
| Visual Object Tracking | 50 videos dataset (test) | Mean Precision (20px)73.2 | 10 | |
| Video Compression Decoding | Videos 1080p | FPS12.5 | 8 | |
| Video-to-Music Generation | Short- and Mid-length Videos | EDC3.11 | 5 | |
| Text-guided Video Editing | 24 videos (full) | Text Alignment (CLIP)0.801 | 5 | |
| Text-Guided Video Editing | 11 videos (test) | Frame Accuracy100 | 4 | |
| Video-to-Video Translation | 23 videos (test) | Frame Accuracy97.8 | 4 | |
| Video Compression | 1080p videos VTM anchor (average) | Average BD-Rate-21.3 | 4 | |
| Zero-shot Video Translation | 23 videos (test) | Frame Accuracy97.8 | 4 | |
| Video Flickering Reduction | Videos (Processed) | Ewarp0.094 | 3 |