Accuracy and Performance Comparison of Video Action Recognition Approaches
Autor: | Chansup Byun, William Arcand, Antonio Rosa, Vijay Gadepally, Matthew Hubbell, David Bestor, Micheal Houle, Matthew Hutchinson, Peter Michaleas, Charles Yee, Andrew Kirby, Julie Mullen, Bill Bergeron, Lauren Milechin, Albert Reuther, Jeremy Kepner, Micheal Jones, Andrew Prout, Siddharth Samsi |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Inference 02 engineering and technology Machine learning computer.software_genre Machine Learning (cs.LG) Consistency (database systems) 0202 electrical engineering electronic engineering information engineering Hyperparameter Computer Science - Performance Artificial neural network business.industry Deep learning 020207 software engineering Performance (cs.PF) Performance comparison Metric (mathematics) Action recognition 020201 artificial intelligence & image processing Artificial intelligence business computer |
Zdroj: | HPEC |
Popis: | 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. Accepted for publication at IEEE HPEC 2020 |
Databáze: | OpenAIRE |
Externí odkaz: |