The Action Bank method is a high-level representation of activity in video. In short, it embeds a video into an "action space" spanned by various action detector responses (correlation/similarity volumes), such as walking-to-the-left, drumming-quickly, etc. The individual action detectors are template based detectors using the action spotting work of Derpanis et al. CVPR 2010. Each individual action detector correlation video volume is transformed into a response vector by volumetric max-pooling (3-levels for a 73-dimension vector). in this library and methods there are 205 action detector templates in the bank, sampled broadly in semantic and viewpoint space.
This package includes the core code, action bank templates, example code for taking the action bank representation and learning a one vs. all linear SVM classifier, example scripts for running over some typical data sets.
The software is free for non-commercial use. See LICENSE for more details.