Video Understanding on LONGVIDEOBENCH TEXT-ONLY
77.17AccuracyVSI-DETECTOR
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| VSI-DETECTORTraining Required=Training Free, Video Search=YOLO-World-110M, Text Encoding=ALL-MPNET-BASE-V2, Frame=642025.08 | 77.17 | 36.8 | 28.37 | 34.44 | |
| T*-DETECTORTraining Required=Training Free, Video Search=YOLO-World-110M, Text Encoding=N/A, Frame=642025.08 | 66.36 | 31.7 | 26.8 | 27.99 | |
| VSLS-DETECTORTraining Required=Training Free, Video Search=YOLO-World-110M, Text Encoding=N/A, Frame=642025.08 | 66.36 | 33.3 | 26.39 | 28.77 |