Action Grounding on YouCook-Interactions (val)
60.05AccuracyVideoGEM
Evaluation Results
| Method | Links | |
|---|---|---|
| VideoGEMBackbone=OpenCLIP, Backbone Pretraining Data=LAION2B, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 60.05 | |
| WWW-CLIPBackbone=CLIP*, Backbone Pretraining Data=WIT-400M, Grounding Training Data=HT100M, Grounding Supervision Type=vision-text pairs only2025.03 | 58.35 | |
| WWW-CLIPBackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=HT100M, Grounding Supervision Type=vision-text pairs only2025.03 | 57.1 | |
| GEMBackbone=OpenCLIP, Backbone Pretraining Data=LAION2B, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 56.87 | |
| VideoGEMBackbone=ViCLIP, Backbone Pretraining Data=InternVid-FLT-10M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 55.1 | |
| VideoGEMBackbone=ViCLIP, Input Type=video2025.03 | 55.1 | |
| GEMBackbone=ViCLIP, Backbone Pretraining Data=InternVid-FLT-10M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 53.62 | |
| GLIPBackbone=Swin-L*, Backbone Pretraining Data=FourODs, GoldG, Cap24M, Grounding Training Data=None, Grounding Supervision Type=localization supervision2025.03 | 52.84 | |
| COMMABackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=HT100M, Grounding Supervision Type=vision-text pairs only2025.03 | 52.65 | |
| VideoGEMBackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 52.57 | |
| RegionCLIPBackbone=RN50x4*, Backbone Pretraining Data=WIT-400M, Grounding Training Data=CC3M, Grounding Supervision Type=vision-text pairs only2025.03 | 51.56 | |
| GEMBackbone=CLIP, Backbone Pretraining Data=WIT-400M, Grounding Training Data=None, Grounding Supervision Type=no training for grounding2025.03 | 50.08 | |
| Qwen-VLPrompt Template=Generate grounding for2025.03 | 28.49 |