Embarrassingly Simple Model for Early Action Proposal

Early action proposal consists in generating high quality candidate temporal segments that are likely to contain an action in a video stream, as soon as they happen. Many sophisticated approaches have been proposed for the action proposal problem but from the off-line perspective. On the contrary, we focus on the on-line version of the problem, proposing a simple classifier-based model, using standard 3D CNNs, that performs significantly better than the state of the art.