Abstract
Hough-transform based voting has been successfully applied to both ob ject and activity detections. However, most current Hough voting methods will suffer when insufficient training data is provided. To address this problem, we propose propagative Hough voting for activity analysis. Instead of letting local features vote individually, we perform feature voting using random pro jection trees (RPT) which leverage the low-dimension manifold structure to match feature points in the high- dimensional feature space. Our RPT can index the unlabeled feature points in an unsupervised way. After the trees are constructed, the la- bel and spatial-temporal configuration information are propagated from the training samples to the testing data via RPT. The proposed activity recognition method does not rely on human detection and tracking, and can well handle the scale and intra-class variations of the activity pat- terns. The superior performances on two benchmarked activity datasets validate that our method outperforms the state-of-the-art techniques not only when there is sufficient training data such as in activity recognition, but also when there is limited training data such as in activity search with one query example.