Temporal Video Grounding on LongVALE
45.7mIoUPadCaptioner
Evaluation Results
| Method | Links | |
|---|---|---|
| PadCaptionerModel Size=3B2026.07 | 45.7 | |
| ChronusOmniModel Size=7B2026.07 | 34.5 | |
| TrisenseModel Size=7B2026.07 | 11.2 | |
| LongVALE-LLMModel Size=7B2026.07 | 11 | |
| VideoChatGPTModel Size=7B2026.07 | 5 | |
| VideoChatModel Size=7B2026.07 | 3 |