Learning action primitives for multi-level video event understanding

Resource type
Thesis type
(Thesis) M.Sc.
Date created
2015-12-21
Authors/Contributors
Author: Chen, Lei
Abstract
Human action categories exhibit significant intra-class variation. Changes in viewpoint, human appearance, and the temporal evolution of an action confound recognition algorithms. In order to address this, we present an approach to discover action primitives, sub-categoriesof action classes, that allow us to model this intra-class variation. We learn action primitives and their interrelations in a multi-level spatio-temporal model for action recognition. Action primitives are discovered via a data-driven clustering approach that focuses on repeatable,discriminative sub-categories. Higher-level interactions between action primitives and the actions of a set of people present in a scene are learned. Empirical results demonstrate that these action primitives can be effectively localized, and using them to model action classesimproves action recognition performance on challenging datasets.
Document
Identifier
etd9391
Copyright statement
Copyright is held by the author.
Permissions
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Scholarly level
Supervisor or Senior Supervisor
Thesis advisor: Mori, Greg
Member of collection
Attachment Size
etd9391_LChen.pdf 9.68 MB