Tasks
SotA
Datasets
Papers
Methods
Submit
About
Datasets
/
UCF-101
UCF-101
Benchmarks
Action Recognition
/
3-fold Accuracy
Action Recognition
/
Accuracy
Activity Recognition
/
3-fold Accuracy
Activity Recognition
/
Accuracy
Text-to-Video Generation
/
FVD16
Video
/
FVD16
Video
/
FVD128
Video
/
Inception Score
Video
/
KVD16
Video Generation
/
FVD16
Video Generation
/
FVD128
Video Generation
/
Inception Score
Video Generation
/
KVD16
Related Benchmarks
UCF-101 16 frames, 128x128, Unconditional
/
Video
/
Inception Score
UCF-101 16 frames, 128x128, Unconditional
/
Video Generation
/
Inception Score
UCF-101 16 frames, 64x64, Unconditional
/
Video
/
FID
UCF-101 16 frames, 64x64, Unconditional
/
Video
/
FVD
UCF-101 16 frames, 64x64, Unconditional
/
Video
/
Inception Score
UCF-101 16 frames, 64x64, Unconditional
/
Video Generation
/
FID
UCF-101 16 frames, 64x64, Unconditional
/
Video Generation
/
FVD
UCF-101 16 frames, 64x64, Unconditional
/
Video Generation
/
Inception Score
UCF-101 16 frames, Unconditional, Single GPU
/
Video
/
Inception Score
UCF-101 16 frames, Unconditional, Single GPU
/
Video Generation
/
Inception Score