Context-aware classification for incremental scene interpretation

Arne Kreutzmann*, Bernd Neumann, Kasim Terzic

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Appearance-based classification is a difficult task in many domains due to ambiguous evidence. Knowledge about the relationships between objects in the scene can help resolve this problem. In this paper, we present a new probabilistic classification framework based on the cooperation of decision trees and Bayesian Compositional Hierarchies, and show that introducing contextual knowledge in the form of dynamic priors significantly improves classification performance in the façade domain.

Original languageEnglish
Title of host publicationWorkshop on Use of Context in Vision Processing, UCVP 2009, in conjunction with 11th Int. Conf. on Multimodal Interfaces and Workshop on Machine Learning for Multi-modal Interaction, ICMI-MLMI 2009
DOIs
Publication statusPublished - 1 Dec 2009
EventWorkshop on Use of Context in Vision Processing, UCVP 2009, in conjunction with 11th International Conference on Multimodal Interfaces and Workshop on Machine Learning for Multi-modal Interaction, ICMI-MLMI 2009 - Boston, MA, United States
Duration: 2 Nov 20096 Nov 2009

Conference

ConferenceWorkshop on Use of Context in Vision Processing, UCVP 2009, in conjunction with 11th International Conference on Multimodal Interfaces and Workshop on Machine Learning for Multi-modal Interaction, ICMI-MLMI 2009
Country/TerritoryUnited States
CityBoston, MA
Period2/11/096/11/09

Keywords

  • Context-driven event interpretation
  • Guided vision based on high-level reasoning

Fingerprint

Dive into the research topics of 'Context-aware classification for incremental scene interpretation'. Together they form a unique fingerprint.

Cite this