Hierarchical graphical models for activity recognition in videos Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/bg257h75k

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • This dissertation addresses the problem of recognizing human activities in videos. Our focus is on activities with stochastic structure, where the activities are characterized by variable space-time arrangements of actions, and conducted by a variable number of actors. These activities occur frequently in sports and surveillance videos. They may appear jointly in multiple instances, at different spatial and temporal scales, under occlusion, and amidst background clutter. These challenges have never been addressed in the literature. Our hypothesis is that these challenges can be successfully addressed using expressive, hierarchical models explicitly encoding activity parts and their spatio-temporal relations. Our hypothesis is formalized using two novel paradigms. One specifies a new constrained hierarchical model of activities allowing efficient activity recognition. Specifically, we formulate Sum-Product Networks (SPNs) for modeling activities, and develop two new learning algorithms using variational learning. The other paradigm considers a more expressive (unconstrained) hierarchical model, And-Or Graphs (AOGs), requiring cost-efficient algorithms for activity recognition. In particular, we develop a new, Monte Carlo Tree Search based inference of AOGs. Our theoretical and empirical studies advance computer vision through demonstrated advantages of each paradigm, compared to the state-of-the-art.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2014-06-17T20:55:50Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) AmerMohamedR2014.pdf: 63853650 bytes, checksum: 168ffde03c157091319df0506f662bf2 (MD5)
  • description.provenance : Submitted by Mohamed Amer (amerm@onid.orst.edu) on 2014-06-06T01:11:04Z No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) AmerMohamedR2014.pdf: 63853650 bytes, checksum: 168ffde03c157091319df0506f662bf2 (MD5)
  • description.provenance : Made available in DSpace on 2014-06-17T20:55:50Z (GMT). No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) AmerMohamedR2014.pdf: 63853650 bytes, checksum: 168ffde03c157091319df0506f662bf2 (MD5) Previous issue date: 2014-05-19
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2014-06-07T18:31:23Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) AmerMohamedR2014.pdf: 63853650 bytes, checksum: 168ffde03c157091319df0506f662bf2 (MD5)

Relationships

In Administrative Set:
Last modified: 08/09/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items