Frugal Forests : learning a dynamic and cost sensitive feature extraction policy for anytime activity classification

Simple item page
dc.contributor.advisorGrauman, Kristen Lorraine, 1979-
dc.creatorKelle, Joshua Allen
dc.date.accessioned2018-10-12T15:39:06Z
dc.date.available2018-10-12T15:39:06Z
dc.date.created2017-05
dc.date.issued2017-05
dc.date.submittedMay 2017
dc.date.updated2018-10-12T15:39:07Z
dc.description.abstractMany approaches to activity classification use supervised learning and so rely on extracting some form of features from the video. This feature extraction process can be computationally expensive. To reduce the cost of feature extraction while maintaining acceptable accuracy, we provide an anytime framework in which features are extracted one by one according to some policy. We propose our novel Frugal Forest feature extraction policy which learns a dynamic and cost sensitive ordering of the features. Cost sensitivity allows the policy to balance features’ predictive power with their extraction cost. The tree-like structure of the forest allows the policy to adjust on the fly in response to previously extracted feature values. We show through several experiments that the Frugal Forest policy exceeds or matches the classification accuracy per unit time of several baselines, including the current state of the art, on two challenging datasets and a variety of feature spaces.
dc.description.departmentComputer Science
dc.format.mimetypeapplication/pdf
dc.identifierdoi:10.15781/T2R49GV2N
dc.identifier.urihttp://hdl.handle.net/2152/68857
dc.language.isoen
dc.subjectFrugal Forest
dc.subjectFeature extraction
dc.subjectActivity recognition
dc.subjectCost
dc.subjectDynamic
dc.titleFrugal Forests : learning a dynamic and cost sensitive feature extraction policy for anytime activity classification
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentComputer Sciences
thesis.degree.disciplineComputer Science
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.levelMasters
thesis.degree.nameMaster of Science in Computer Sciences

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
KELLE_THESIS_2017.pdf
Size:
3.1 MB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.45 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.84 KB
Format:
Plain Text
Description:
Download

Collections

UT Electronic Theses and Dissertations