Semantic-Shift for Unsupervised Object Detection

Authors:
David Liu;Tsuhan Chen
Affiliations:
Carnegie Mellon University, USA;Carnegie Mellon University, USA
Venue:
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Year:
2006

Citing 0
Cited 10

Video retrieval based on object discovery

Computer Vision and Image Understanding
Unsupervised modeling of objects and their hierarchical contextual interactions

Journal on Image and Video Processing - Special issue on patches in vision
Foreground Focus: Unsupervised Learning from Partially Matching Images

International Journal of Computer Vision
Learning natural scene categories by selective multi-scale feature extraction

Image and Vision Computing
Unsupervised identification of multiple objects of interest from multiple images: dISCOVER

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
A spatially aware generative model for image classification, topic discovery and segmentation

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Semantics extraction from images

Knowledge-driven multimedia information extraction and ontology evolution
Probabilistic semantic component descriptor

Multimedia Tools and Applications
A region-centered topic model for object discovery and category-based image segmentation

Pattern Recognition
Moving people tracking with detection by latent semantic analysis for visual surveillance applications

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The bag of visual words representation has attracted a lot of attention in the computer vision community. In particular, Probabilistic Latent Semantic Analysis (PLSA) has been applied to object recognition as an unsupervised technique built on top of the bag of visual words representation. PLSA, however, does not explicitly consider the spatial information of the visual words. In this paper, we propose an iterative technique, where a modified form of PLSA provides location and scale estimates of the foreground object through the estimated latent semantic. In return, the updated location and scale estimates will improve the estimate of the latent semantic. We call this iterative algorithm Semantic-Shift. We show results with significant improvements over PLSA.