Structured concept recycling by probabilistic logic ontology tree

"Recent advances in multimedia research have generated a large collection of concept models, e.g., LSCOM and Mediamill 101, which have become accessible to other researchers. While most current research efforts still focus on building new concepts from scratch, little effort has been made to construct new concepts upon the existing models already in the ""warehouse"". To address this issue, we have developed a new framework in this thesis, termed LEarning structured model by probabilistic loGic Ontology (LEGO) to seamlessly integrate both the new target training examples and the existing primitive concept models. LEGO treats the primitive concept models as a Lego toy to potentially construct an unlimited vocabulary of new concepts. Specifically, LEGO first formulates the logic operations to be the Lego connectors used to combine existing concept models hierarchically in probabilistic logic ontology trees. LEGO then simultaneously incorporates new target training information to efficiently disambiguate the underlying logic tree and correct the error propagation. We present extensive experimental results on a large vehicle domain data set from ImageNet and demonstrate significantly superior performance over existing state-of-the-art approaches which build new concept models from scratch."

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2014

Author dc:creator

• Chang, Shiyu

Contributors dc:contributor

• Huang, Thomas S.

• Multimedia LEarning structured model by probabilistic loGic Ontology (LEGO)
• Concept recycling
• Model warehouse
• Probabilistic logic ontology tree
• Logical operations

Statement dc:rights

• Copyright 2013 Shiyu Chang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/46848

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/46848