Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection

Open paper
Benchmark Model Rank Results
skeleton-based-action-recognition-on-j-hmdbChained (RGB+Flow +Pose)#3Accuracy (RGB+pose): 76.1Accuracy (pose): 56.8
skeleton-based-action-recognition-on-jhmdb-2d-poses-onlyChained#5Average accuracy of 3 splits: 56.8

Rank counts only results with a code link.