Image Classification Using Super-Vector Coding of Local Image Descriptors

Abstract

This paper introduces a new framework for image classification using local visual descriptors. The pipeline first performs a nonlinear feature transformation on descriptors, then aggregates the results together to form image-level representations, and finally applies a classification model. For all the three steps we suggest novel solutions which make our approach appealing in theory, more scalable in computation, and transparent in classification. Our experiments demonstrate that the proposed classification method achieves state-of-the-art accuracy on the well-known PASCAL benchmarks.

Cite

Text

Zhou et al. "Image Classification Using Super-Vector Coding of Local Image Descriptors." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15555-0_11

Markdown

[Zhou et al. "Image Classification Using Super-Vector Coding of Local Image Descriptors." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/zhou2010eccv-image/) doi:10.1007/978-3-642-15555-0_11

BibTeX

@inproceedings{zhou2010eccv-image,
  title     = {{Image Classification Using Super-Vector Coding of Local Image Descriptors}},
  author    = {Zhou, Xi and Yu, Kai and Zhang, Tong and Huang, Thomas S.},
  booktitle = {European Conference on Computer Vision},
  year      = {2010},
  pages     = {141-154},
  doi       = {10.1007/978-3-642-15555-0_11},
  url       = {https://mlanthology.org/eccv/2010/zhou2010eccv-image/}
}