GroundedInter
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Human-Object Interaction Video Generation | GroundedInter Audio-Driven 1.0 (test) | VLM-QA0.2732 | 5 | |
| Human-Object Interaction Video Generation | GroundedInter Text-Driven 1.0 (test) | VLM-QA29.07 | 4 | |
| Human-Object Interaction Video Generation | GroundedInter Pose-Driven 1.0 (test) | VLM-QA28.47 | 2 |
Showing 3 of 3 rows