TOMATO
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Understanding | Tomato (test) | Accuracy0.53 | 43 | |
| Temporal video understanding | TOMATO | Accuracy53 | 20 | |
| Video Understanding | TOMATO | Score60.8 | 18 | |
| Video Motion & Perception | TOMATO | Accuracy95.2 | 13 | |
| Exocentric Video Understanding | Tomato | Score34.5 | 13 | |
| General Video Understanding | TOMATO | Accuracy37.7 | 13 | |
| Short Video Question Answering | TOMATO (test) | Accuracy42 | 12 | |
| Action-Attribute Recognition | TOMATO | Accuracy53 | 11 | |
| Motion Understanding and Temporal Reasoning | Tomato (test) | Accuracy53 | 10 | |
| Complex Reasoning | TOMATO | Accuracy38.1 | 9 | |
| Theory of Mind | ToMATO | Accuracy82.2 | 9 | |
| Crop disease diagnosis | Tomato 20 classes | Accuracy76.1 | 8 | |
| Video Question Answering | TOMATO | Score35.58 | 8 | |
| De novo peptide sequencing | Tomato | AA Precision82.2 | 7 | |
| Reinforcement Learning | Tomato | True Score6.28 | 3 | |
| Short video understanding | TOMATO | Accuracy46.9 | 3 | |
| Orientation-aware robotic grasping and placement | Tomato Single-object (Isolated Environment) | Time (s)8.3 | 2 | |
| Plant Disease Classification | Tomato-5 1.0 (test) | Accuracy0.7666 | 2 |
Showing 18 of 18 rows