Spatio Temporal Video Grounding On Hc Stvg1
Metrics
m_vIoU
vIoU@0.3
vIoU@0.5
Results
Performance results of various models on this benchmark
Comparison Table
Model Name | m_vIoU | vIoU@0.3 | vIoU@0.5 |
---|---|---|---|
knowing-your-target-target-aware-transformer | 39.1 | 63.1 | 36.8 |
tubedetr-spatio-temporal-video-grounding-with | 32.4 | 49.8 | 23.5 |
context-guided-spatio-temporal-video | 38.4 | 61.5 | 36.3 |