Objects as attributes for scene classification

  • Authors:

  • Li-Jia Li;Hao Su;Yongwhan Lim;Li Fei-Fei

  • Affiliations:

  • Computer Science Department, Stanford University;Computer Science Department, Stanford University;Computer Science Department, Stanford University;Computer Science Department, Stanford University

  • Venue:
  • ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Robust low-level image features have proven to be effective representations for a variety of high-level visual recognition tasks, such as object recognition and scene classification. But as the visual recognition tasks become more challenging, the semantic gap between low-level feature representation and the meaning of the scenes increases. In this paper, we propose to use objects as attributes of scenes for scene classification. We represent images by collecting their responses to a large number of object detectors, or "object filters". Such representation carries high-level semantic information rather than low-level image feature information, making it more suitable for high-level visual recognition tasks. Using very simple, off-the-shelf classifiers such as SVM, we show that this object-level image representation can be used effectively for high-level visual tasks such as scene classification. Our results are superior to reported state-of-the-art performance on a number of standard datasets.