Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs

Benchmark Model Rank Results
action-classification-on-charadesHAF+BoW/FV/OFF halluc. +MSK×8/PN–MAP: 43.1
action-recognition-in-videos-on-hmdb-51HAF+BoW/FV halluc–Average accuracy of 3 splits: 82.48
scene-recognition-on-yup-plus-plusHAF+BoW/FV halluc.–Accuracy (%): 92.6