Representing and recognizing objects with massive local image patches

DOI10.1016/J.PATCOG.2011.06.011MaRDI QIDQ645863zbMATHOpenAlexFDO

Authors Liang Lin, Ping Luo, Xiaowu Chen, Kun Zeng

Publication date 10 November 2011

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.patcog.2011.06.011

zbMATH Keywords

object recognitionobject detectiongenerative learning

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies for image processing (68U10)

Recommendations

• Object Recognition via Local Patch Labelling
• Object categorization
• scientific article; zbMATH DE number 2090832
• How to explore the patch space
• Learning features for robust object recognition.

Cites work

• scientific article; zbMATH DE number 2062490 (Why is no real title available?)
• A decision-theoretic generalization of on-line learning and an application to boosting
• A stochastic graph grammar for compositional object representation and recognition
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)

Cited in

(8)

• Object Recognition via Local Patch Labelling
• Combinatorial and statistical methods for part selection for object recognition
• Efficient patch-level descriptor for image categorization via patch pivots selection
• Image classification with the Fisher vector: theory and practice
• Hierarchical mixing linear support vector machines for nonlinear classification
• How to explore the patch space
• Maximum likelihood features for generative image models
• Mining mid-level visual patterns with deep CNN activations

Describes a project that uses

Uses Software

• AdaBoost.MH
• SIFT
• I2T

This page was built for publication: Representing and recognizing objects with massive local image patches

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q645863)