Variations of a Hough-Voting Action Recognition System

Abstract

This paper presents two variations of a Hough-voting framework used for action recognition and shows classification results for lowresolution video and videos depicting human interactions. For low-resolution videos, where people performing actions are around 30 pixels, we adopt low-level features such as gradients and optical flow. For group actions with human-human interactions, we take the probabilistic action labels from the Hough-voting framework for single individuals and combine them into group actions using decision profiles and classifier combination.

DOI: 10.1007/978-3-642-17711-8_31
View Slides

Extracted Key Phrases

4 Figures and Tables

0102020102011201220132014201520162017
Citations per Year

64 Citations

Semantic Scholar estimates that this publication has 64 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Waltisberg2010VariationsOA, title={Variations of a Hough-Voting Action Recognition System}, author={Daniel Waltisberg and Angela Yao and Juergen Gall and Luc Van Gool}, booktitle={ICPR Contests}, year={2010} }