book

Learning-Based Local Visual Representation and Indexing

by Rongrong Ji, Yue Gao, Ling-Yu Duan, Hongxun Yao, Qionghai Dai

April 2015

Intermediate to advanced

128 pages

3h 45m

English

Morgan Kaufmann

Read now

Unlock full access

Abstract1.1 Background and Significance1.2 Literature Review of the Visual Dictionary1.3 Contents of this Book
Abstract2.1 Introduction2.2 Difference of Contextual Gaussians2.3 Mean Shift-Based Localization2.4 Detector Learning2.5 Experiments2.6 Summary

Abstract3.1 Introduction3.2 Density-Based Metric Learning3.3 Chain-Structure Recognition3.4 Dictionary Transfer Learning3.5 Experiments3.6 Summary
Abstract4.1 Introduction4.2 Semantic Labeling Propagation4.3 Supervised Dictionary Learning4.4 Experiments4.5 Summary
Abstract5.1 Introduction5.2 Discriminative 3D Pattern Mining5.3 CBoP for Low Bit Rate Mobile Visual Search5.4 Quantitative Results5.5 Conclusion

Overview

Learning-Based Local Visual Representation and Indexing, reviews the state-of-the-art in visual content representation and indexing, introduces cutting-edge techniques in learning based visual representation, and discusses emerging topics in visual local representation, and introduces the most recent advances in content-based visual search techniques.

Discusses state-of-the-art procedures in learning-based local visual representation.
Shows how to master the basic techniques needed for building a large-scale visual search engine and indexing system
Provides insight into how machine learning techniques can be leveraged to refine the visual recognition system, especially in the part of visual feature representation.