Human Action Recognition using Local Two-Stream Convolution Neural Network Features and Support Vector Machines

TL;DR

This paper introduces a human action recognition method that combines local appearance and motion features extracted via 3D CNNs, then classifies actions with an SVM, demonstrating improved accuracy on benchmark datasets.

Contribution

It presents a novel approach that integrates local features from 3D CNNs with SVM classification and simple preprocessing techniques for enhanced action recognition.

Findings

SVM improves classification accuracy over other classifiers.

Preprocessing techniques like optical flow scaling and crop filling boost performance.

Method achieves competitive results on benchmark datasets.

Abstract

This paper proposes a simple yet effective method for human action recognition in video. The proposed method separately extracts local appearance and motion features using state-of-the-art three-dimensional convolutional neural networks from sampled snippets of a video. These local features are then concatenated to form global representations which are then used to train a linear SVM to perform the action classification using full context of the video, as partial context as used in previous works. The videos undergo two simple proposed preprocessing techniques, optical flow scaling and crop filling. We perform an extensive evaluation on three common benchmark dataset to empirically show the benefit of the SVM, and the two preprocessing steps.