A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset

Abstract

This paper aims to determine which is the best human action recognition method based on features extracted from RGB-D devices, such as the Microsoft Kinect. A review of all the papers that make reference to MSR Action3D, the most used dataset that includes depth information acquired from a RGB-D device, has been performed. We found that the validation method used by each work differs from the others. So, a direct comparison among works cannot be made. However, almost all the works present their results comparing them without taking into account this issue. Therefore, we present different rankings according to the methodology used for the validation in orden to clarify the existing confusion.

arXiv comment16 pages and 7 tables

References in corpus (2)

• Unstructured Human Activity Detection from RGBD Images
• Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences

Cited by in corpus (4)

• Space-Time Representation of People Based on 3D Skeletal Data: A Review
• Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions
• Stats-Calculus Pose Descriptor Feeding A Discrete HMM Low-latency Detection and Recognition System For 3D Skeletal Actions
• Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences