SHG-VQA (trained from scratch)
Reported on 2 benchmarks across 1 task · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Reasoning2 results
- Average Accuracy· 2023-04-1849.2best: 55.08 (GF (sup) - Faster RCNN)
- Average Accuracy· 2023-04-1839.47best: 67.1 (VLAP (4 frames))