HyperAI

Spatio Temporal Video Grounding On Vidstg

Metriken

Declarative m_vIoU
Declarative vIoU@0.3
Declarative vIoU@0.5
Interrogative m_vIoU
Interrogative vIoU@0.3
Interrogative vIoU@0.5

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Vergleichstabelle
ModellnameDeclarative m_vIoUDeclarative vIoU@0.3Declarative vIoU@0.5Interrogative m_vIoUInterrogative vIoU@0.3Interrogative vIoU@0.5
tubedetr-spatio-temporal-video-grounding-with30.442.528.225.735.723.2
knowing-your-target-target-aware-transformer34.448.233.529.541.528.0
context-guided-spatio-temporal-video34.047.733.129.040.527.5