TubeDETR: Spatio-Temporal Video Grounding with Transformers

Benchmark Model Rank Results
spatio-temporal-video-grounding-on-hc-stvg1TubeDETR#3m_vIoU: 32.4vIoU@0.3: 49.8vIoU@0.5: 23.5
spatio-temporal-video-grounding-on-hc-stvg2TubeDETR#3Val m_vIoU: 36.4Val vIoU@0.3: 58.8Val vIoU@0.5: 30.6
spatio-temporal-video-grounding-on-vidstgTubeDETR#3Declarative m_vIoU: 30.4Declarative vIoU@0.3: 42.5