Applying high performance computing to early fusion video action recognition
Name
1192561136-MIT.pdf
Size
3.83 MB
Format
Adobe PDF
Checksum (MD5)
304f6d0479cfd78b0266229d29d591c4
Author(s)
Hutchinson, Matthew S.,M. Eng.Massachusetts Institute of Technology.
Advisor(s)
Charles E. Leiserson and Vijay Gadepally.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
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. Additionally, the literature demonstrates a fixedness on late fusion approaches to audio-video multimodal problems. This project provides a side-by-side comparison of several 2-Dimensional Convolutional Neural Network (2D-CNN) video action recognition approaches and investigates the effectiveness and efficiency of new audio-video early fusion, slicing, and sampling methods. Model accuracy is evaluated using standard Top-1 and Top-5 metrics in addition to novel p-ROC metrics, and this project demonstrates the usefulness of the latter. Computational performance is measured via total training time and training time per epoch on a variety of high-performance computing (HPC) training configurations.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 91-99).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
Persistent DSpace Link
