HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN
Open paper
Benchmark
Model
Rank
Results
action-recognition-in-videos-on-ucf101
HalluciNet (ResNet-50)
#53
3-fold Accuracy: 79.83
scene-recognition-on-yup-plus-plus
HalluciNet (ResNet-50)
#1
Accuracy (%): 84.44
Rank counts only results with a code link.