Action Recognition in Video Using Sparse Coding and Relative Features

TL;DR

This paper introduces a novel sparse coding-based method for action recognition in videos, utilizing a new descriptor called ITRA that captures relative similarities among key-sequences, leading to superior performance on benchmark datasets.

Contribution

It proposes a new approach combining sparse coding with the ITRA descriptor to handle intra-class variations and improve action recognition accuracy.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively captures intra- and inter-class similarities.

Demonstrates high discriminative power of the ITRA descriptor.

Abstract

This work presents an approach to category-based action recognition in video using sparse coding techniques. The proposed approach includes two main contributions: i) A new method to handle intra-class variations by decomposing each video into a reduced set of representative atomic action acts or key-sequences, and ii) A new video descriptor, ITRA: Inter-Temporal Relational Act Descriptor, that exploits the power of comparative reasoning to capture relative similarity relations among key-sequences. In terms of the method to obtain key-sequences, we introduce a loss function that, for each video, leads to the identification of a sparse set of representative key-frames capturing both, relevant particularities arising in the input video, as well as relevant generalities arising in the complete class collection. In terms of the method to obtain the ITRA descriptor, we introduce a novel scheme to quantify relative intra and inter-class similarities among local temporal patterns arising in the videos. The resulting ITRA descriptor demonstrates to be highly effective to discriminate among action categories. As a result, the proposed approach reaches remarkable action recognition performance on several popular benchmark datasets, outperforming alternative state-of-the-art techniques by a large margin.