You are here

Recognition of Complex Events in Open-source Web-scale Videos: Features, Intermediate Representations and their Temporal Interactions

Download pdf | Full Screen View

Date Issued:
2013
Abstract/Description:
Recognition of complex events in consumer uploaded Internet videos, captured under real-world settings, has emerged as a challenging area of research across both computer vision and multimedia community. In this dissertation, we present a systematic decomposition of complex events into hierarchical components and make an in-depth analysis of how existing research are being used to cater to various levels of this hierarchy and identify three key stages where we make novel contributions, keeping complex events in focus. These are listed as follows: (a) Extraction of novel semi-global features -- firstly, we introduce a Lie-algebra based representation of dominant camera motion present while capturing videos and show how this can be used as a complementary feature for video analysis. Secondly, we propose compact clip level descriptors of a video based on covariance of appearance and motion features which we further use in a sparse coding framework to recognize realistic actions and gestures. (b) Construction of intermediate representations -- We propose an efficient probabilistic representation from low-level features computed from videos, basedon Maximum Likelihood Estimates which demonstrates state of the art performancein large scale visual concept detection, and finally, (c) Modeling temporal interactions between intermediate concepts -- Using block Hankel matrices and harmonic analysis of slowly evolving Linear Dynamical Systems, we propose two new discriminative feature spaces for complex event recognition and demonstratesignificantly improved recognition rates over previously proposed approaches.
Title: Recognition of Complex Events in Open-source Web-scale Videos: Features, Intermediate Representations and their Temporal Interactions.
14 views
7 downloads
Name(s): Bhattacharya, Subhabrata, Author
Shah, Mubarak, Committee Chair
Guha, Ratan, Committee Member
Laviola II, Joseph, Committee Member
Sukthankar, Rahul, Committee Member
Moore, Brian, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2013
Publisher: University of Central Florida
Language(s): English
Abstract/Description: Recognition of complex events in consumer uploaded Internet videos, captured under real-world settings, has emerged as a challenging area of research across both computer vision and multimedia community. In this dissertation, we present a systematic decomposition of complex events into hierarchical components and make an in-depth analysis of how existing research are being used to cater to various levels of this hierarchy and identify three key stages where we make novel contributions, keeping complex events in focus. These are listed as follows: (a) Extraction of novel semi-global features -- firstly, we introduce a Lie-algebra based representation of dominant camera motion present while capturing videos and show how this can be used as a complementary feature for video analysis. Secondly, we propose compact clip level descriptors of a video based on covariance of appearance and motion features which we further use in a sparse coding framework to recognize realistic actions and gestures. (b) Construction of intermediate representations -- We propose an efficient probabilistic representation from low-level features computed from videos, basedon Maximum Likelihood Estimates which demonstrates state of the art performancein large scale visual concept detection, and finally, (c) Modeling temporal interactions between intermediate concepts -- Using block Hankel matrices and harmonic analysis of slowly evolving Linear Dynamical Systems, we propose two new discriminative feature spaces for complex event recognition and demonstratesignificantly improved recognition rates over previously proposed approaches.
Identifier: CFE0004817 (IID), ucf:49724 (fedora)
Note(s): 2013-08-01
Ph.D.
Engineering and Computer Science, Electrical Engineering and Computing
Doctoral
This record was generated from author submitted information.
Subject(s): Complex Event recognition -- Multimedia Event Detection -- Covariance Matrices -- Lie Algebra -- Riemannian manifolds -- Cinematographic Techniques -- Shot classification -- Video Descriptors -- Maximum Likelihood Estimates -- Linear Dynamical Systems -- Block hankel matrices
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0004817
Restrictions on Access: public 2013-08-15
Host Institution: UCF

In Collections