Theory of Learning with Few Examples and Object Localization

Authors Erik Rodner, Joachim Denzler



PDF
Thumbnail PDF

File

DagSemProc.08422.9.pdf
  • Filesize: 114 kB
  • 0 pages

Document Identifiers

Author Details

Erik Rodner
Joachim Denzler

Cite AsGet BibTex

Erik Rodner and Joachim Denzler. Theory of Learning with Few Examples and Object Localization. In Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes. Dagstuhl Seminar Proceedings, Volume 8422, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2009)
https://doi.org/10.4230/DagSemProc.08422.9

Abstract

Visual object localization and categorization is still a big challenge for current research and gets even more difficult when confronted with few training examples. Therefore we will present a Bayesian concept to enhance state-of-the-art machine learning techniques even when dealing with just a single view of an object category. Furthermore an object localization approach is presented, which can serve as a baseline for researchers within the area of object localization.
Keywords
  • Object detection
  • one-shot learning
  • knowledge transfer

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads