Learning Spatiotemporal Features with 3D Convolutional Networks
Open paper
Benchmark
Model
Rank
Results
action-recognition-in-videos-on-hmdb-51
C3D
#48
Average accuracy of 3 splits: 51.6
action-recognition-in-videos-on-ucf101
C3D
#52
3-fold Accuracy: 82.3
Rank counts only results with a code link.