Modelling Temporal Information Using Discrete Fourier Transform for Video Classification

TL;DR

This paper introduces a novel approach for video classification that combines static CNN features with frequency domain DFT features to effectively model temporal information, leading to improved performance in emotion recognition and action recognition tasks.

Contribution

The paper proposes using DFT features to encode temporal information in videos, enhancing existing CNN-based methods for better classification accuracy.

Findings

Achieved state-of-the-art results on VideoEmotion-8 dataset.

Demonstrated competitive performance on UCF-101.

Showed that DFT features effectively capture temporal dynamics.

Abstract

Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time domain features are transformed and interpolated into DFT features. CNN and DFT features are further encoded by using different pooling methods and fused for video classification. In this way, static image features extracted from a pre-trained deep CNN and temporal information represented by DFT features are jointly considered for video classification. We test our method for video emotion classification and action recognition. Experimental results demonstrate that combining DFT features can effectively capture temporal information and therefore improve the performance of both video emotion classification and action recognition. Our approach has achieved a state-of-the-art performance on the largest video emotion dataset (VideoEmotion-8 dataset) and competitive results on UCF-101.