Title

Action Recognition In Unconstrained Amateur Videos

Keywords

Action recognition; Video analysis; Video indexing

Abstract

In this paper, we propose a systematic framework for action recognition in unconstrained amateur videos. Inspired by the success of local features used in object and pose recognition, we extract local static features from the sampled frames to capture local pose shape and appearance. In addition, we extract spatiotemporal features (ST features), which have been successfully used in action recognition, to capture the local motions. In the action recognition phase, we use the Pyramid Match Kernel based on weighted similarities of multi-resolution histograms to match two videos within the same feature types. In order to handle complementary but heterogeneous features, i.e., static and motion features, we chose a multi-kernel classifier for feature fusion. To reduce the noise introduced by the background clutter, our system also tries to automatically find the rough region of interest/action. Preliminary tests on the KTH action dataset, UCF sports dataset, and a YouTube action dataset have shown promising results. ©2009 IEEE.

Publication Date

9-23-2009

Publication Title

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Number of Pages

3549-3552

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/ICASSP.2009.4960392

Socpus ID

70349207276 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/70349207276

This document is currently not available here.

Share

COinS