Propagative Hough Voting to Leverage Contextual Information

Abstract

Generalized Hough voting has shown promising results in both object and action detection. However, most existing Hough voting methods will suffer when insufficient training data are provided. To address this limitation, we propose propagative Hough voting in this chapter. Instead of training a discriminative classifier for local feature voting, we first match labeled feature points to unlabeled feature points, then propagate the label and sptatio-temporal configuration information via Hough voting. To enable a fast and robust matching, we index the unlabeled data using random projection trees (RPT). RPT can leverage the low-dimension manifold structure to provide adaptive local feature matching. Moreover, as the RPT index can be built in either labeled or unlabeled dataset, it can be applied to different tasks such as action search (limited training) and recognition (sufficient training). The superior performances on benchmarked datasets validate that our propagative Hough voting can outperform state-of-the-art techniques in various action analysis tasks, such as action search and recognition.