Context augmented event and object recognition
Loading...
Authors
Wang, Xiaoyang
Issue Date
2015-05
Type
Electronic thesis
Thesis
Thesis
Language
ENG
Keywords
Electrical engineering
Alternative Title
Abstract
Fourthly, unlike traditional approaches for object recognition that treat attributes as a middle level representation and require the estimation of attributes during testing, we further propose to incorporate attributes as hidden context to improve object recognition. To achieve this goal, we develop two different approaches to incorporate attributes, with one approach utilizing attributes as additional features and the other utilizing the relationships between attributes and objects. Both approaches can effectively improve the learning of the object classifiers, and a combination of the two yields the best performance.
Description
May 2015
School of Engineering
School of Engineering
Full Citation
Publisher
Rensselaer Polytechnic Institute, Troy, NY