Discriminative Dictionary Design for Action Classification in Still Images and Videos

TL;DR

This paper introduces a discriminative dictionary design method for action recognition in images and videos, focusing on selecting category-specific features to improve classification accuracy.

Contribution

It proposes a novel feature selection approach that enhances class separability by identifying robust local descriptors, improving action recognition performance.

Findings

Superior accuracy on Stanford-40 and UCF-50 datasets

Effective feature selection improves class discrimination

Outperforms existing methods in action recognition

Abstract

In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT, STIP etc. invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50) and exhibits superior performances than the representative methods from the literature.