Activity Recognition on UCF101 (Average across 3 splits)
93.5Mean AccuracyTwo-stream fusion architecture (VGG-16, VGG-16) + IDT
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Two-stream fusion architecture (VGG-16, VGG-16) + IDTSpatial (S) network=VGG-16, Temporal (T) network=VGG-16, Hand-crafted features (IDT)=true2016.04 | 93.5 | — | — | — | — | |
| Two-stream fusion architecture (VGG-16, VGG-M) + IDTSpatial (S) network=VGG-16, Temporal (T) network=VGG-M, Hand-crafted features (IDT)=true2016.04 | 92.5 | — | — | — | — | |
| TDD+IDTHand-crafted features (IDT)=true2016.04 | 91.5 | — | — | — | — | |
| C3D+IDTHand-crafted features (IDT)=true2016.04 | 90.4 | — | — | — | — | |
| IDT+higher dimensional FVHand-crafted features (IDT)=true2016.04 | 87.9 | — | — | — | — | |
| LRCNInput Features=fc62014.11 | — | 68.2 | 77.28 | 80.9 | 82.34 | |
| Single frame2014.11 | — | 67.37 | 74.37 | 75.46 | 78.94 |