References https://github.com/jamespark3922/visual-comet https://asu-active-perception-group.github.io/Video2Commonsense/index.html http://www.mindsvsmachines.com/accepted.html https://blog.qure.ai/notes/deep-learning-for-videos-action-recognition-review https://nanonets.com/blog/tag/human-action-recognition/ https://arxiv.org/pdf/1807.11546.pdf