Action Grounding on Grounding YouTube (test)
57.21AccuracyVideoGEM
Evaluation Results
| Method | Links | |
|---|---|---|
| VideoGEMBackbone=ViCLIP, Backbone Pretraining Data=InternVid-FLT-10M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 57.21 | |
| WWW-CLIPBackbone=CLIP*, Backbone Pretraining Data=WIT-400M, Grounding Training Data=HT100M, Grounding Supervision Type=vision-text pairs only2025.03 | 56.98 | |
| WWW-CLIPBackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=HT100M, Grounding Supervision Type=vision-text pairs only2025.03 | 55.49 | |
| GLIPBackbone=Swin-L*, Backbone Pretraining Data=FourODs, GoldG, Cap24M, Grounding Training Data=None, Grounding Supervision Type=localization supervision2025.03 | 53.62 | |
| RegionCLIPBackbone=RN50x4*, Backbone Pretraining Data=WIT-400M, Grounding Training Data=CC3M, Grounding Supervision Type=vision-text pairs only2025.03 | 52.84 | |
| GEMBackbone=ViCLIP, Backbone Pretraining Data=InternVid-FLT-10M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 51.28 | |
| COMMABackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=HT100M, Grounding Supervision Type=vision-text pairs only2025.03 | 47.56 | |
| VideoGEMBackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 47.46 | |
| VideoGEMBackbone=OpenCLIP, Backbone Pretraining Data=LAION2B, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 45.33 | |
| GEMBackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 36.92 | |
| GEMBackbone=OpenCLIP, Backbone Pretraining Data=LAION2B, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 32.91 |