Paper Info
Title
Accuracy and Performance Comparison of Video Action Recognition Approaches
Abstract
Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen “off-the-shelf” and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system.
Year
DOI
Venue
2020
10.1109/HPEC43674.2020.9286249
2020 IEEE High Performance Extreme Computing Conference (HPEC)
Keywords
DocType
ISSN
action recognition,neural network,deep learning,accuracy metrics,computational performance
Conference
2377-6943
ISBN
Citations 
PageRank 
978-1-7281-9220-8
0
0.34
References 
Authors
10
19
Name
Order
Citations
PageRank
Matthew Hutchinson100.34
Siddharth Samsi220124.09
William Arcand317517.77
David Bestor418119.08
Bill Bergeron516816.57
Chansup Byun618019.21
Micheal Houle700.34
Matthew Hubbell819220.93
Micheal Jones900.34
Jeremy Kepner1060661.58
Andrew Kirby1100.34
Peter Michaleas1220120.93
Lauren Milechin1310216.45
Julie Mullen1413815.22
Andrew Prout1518218.78
Antonio Rosa1617017.67
Albert Reuther1733537.32
Charles Yee1814715.14
Vijay Gadepally1944950.53