Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
ORCID
https://orcid.org/0000-0003-4894-3764
Access Type
Open Access Thesis
Document Type
thesis
Degree Program
Electrical & Computer Engineering
Degree Type
Master of Science in Electrical and Computer Engineering (M.S.E.C.E.)
Year Degree Awarded
2020
Month Degree Awarded
September
Abstract
We consider the application of Few-Shot Learning (FSL) and dimensionality reduction to the problem of human motion recognition (HMR). The structure of human motion has unique characteristics such as its dynamic and high-dimensional nature. Recent research on human motion recognition uses deep neural networks with multiple layers. Most importantly, large datasets will need to be collected to use such networks to analyze human motion. This process is both time-consuming and expensive since a large motion capture database must be collected and labeled. Despite significant progress having been made in human motion recognition, state-of-the-art algorithms still misclassify actions because of characteristics such as the difficulty in obtaining large-scale leveled human motion datasets. To address these limitations, we use metric-based FSL methods that use small-size data in conjunction with dimensionality reduction. We also propose a modified dimensionality reduction scheme based on the preservation of secants tailored to arbitrary useful distances, such as the geodesic distance learned by ISOMAP. We provide multiple experimental results that demonstrate improvements in human motion classification.
DOI
https://doi.org/10.7275/18399651
First Advisor
Marco F. Duarte
Second Advisor
Mario Parente
Third Advisor
Hossein Pishro-Nik
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Recommended Citation
Kong, ByoungDoo, "Metric Learning via Linear Embeddings for Human Motion Recognition" (2020). Masters Theses. 973.
https://doi.org/10.7275/18399651
https://scholarworks.umass.edu/masters_theses_2/973
Included in
Computer Engineering Commons, Computer Sciences Commons, Electrical and Computer Engineering Commons