Global Temporal Representation based CNNs for Infrared Action Recognition

by   Yang Liu, et al.

Infrared human action recognition has many advantages, i.e., it is insensitive to illumination change, appearance variability, and shadows. Existing methods for infrared action recognition are either based on spatial or local temporal information, however, the global temporal information, which can better describe the movements of body parts across the whole video, is not considered. In this letter, we propose a novel global temporal representation named optical-flow stacked difference image (OFSDI) and extract robust and discriminative feature from the infrared action data by considering the local, global, and spatial temporal information together. Due to the small size of the infrared action dataset, we first apply convolutional neural networks on local, spatial, and global temporal stream respectively to obtain efficient convolutional feature maps from the raw data rather than train a classifier directly. Then these convolutional feature maps are aggregated into effective descriptors named three-stream trajectory-pooled deep-convolutional descriptors by trajectory-constrained pooling. Furthermore, we improve the robustness of these features by using the locality-constrained linear coding (LLC) method. With these features, a linear support vector machine (SVM) is adopted to classify the action data in our scheme. We conduct the experiments on infrared action recognition datasets InfAR and NTU RGB+D. The experimental results show that the proposed approach outperforms the representative state-of-the-art handcrafted features and deep learning features based methods for the infrared action recognition.



There are no comments yet.


page 1

page 2

page 4


Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition

It remains a challenge to efficiently extract spatialtemporal informatio...

Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier

This paper proposes a new framework for RGB-D-based action recognition t...

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

This paper proposes a simple yet effective method for human action recog...

Slow Feature Analysis for Human Action Recognition

Slow Feature Analysis (SFA) extracts slowly varying features from a quic...

Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN

3D Convolutional Neural Network (3D CNN) captures spatial and temporal i...

Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition

Recently, infrared human action recognition has attracted increasing att...

Learning to Sort Image Sequences via Accumulated Temporal Differences

Consider a set of n images of a scene with dynamic objects captured with...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.