HyperAI

Spatio Temporal Video Grounding On Hc Stvg2

Metrics

Val m_vIoU
Val vIoU@0.3
Val vIoU@0.5

Results

Performance results of various models on this benchmark

Comparison Table
Model NameVal m_vIoUVal vIoU@0.3Val vIoU@0.5
context-guided-spatio-temporal-video39.564.536.3
knowing-your-target-target-aware-transformer40.265.836.7
stvgformer-spatio-temporal-video-grounding38.765.533.8
tubedetr-spatio-temporal-video-grounding-with36.458.830.6