Immediate, Scalable Object Category Detection

Abstract

The objective of this work is object category detection in large scale image datasets in the manner of Video Google — an object category is specified by a HOG classifier template, and retrieval is immediate at run time. We make the following three contributions: (i) a new image representation based on mid-level discriminative patches, that is designed to be suited to immediate object category detection and inverted file indexing; (ii) a sparse representation of a HOG classifier using a set of mid-level discriminative classifier patches; and (iii) a fast method for spatial reranking images on their detections. We evaluate the detection method on the standard PASCAL VOC 2007 dataset, together with a 100K image subset of ImageNet, and demonstrate near state of the art detection performance at low ranks whilst maintaining immediate retrieval speeds. Applications are also demonstrated using an exemplar-SVM for pose matched retrieval.

Cite

Text

Aytar and Zisserman. "Immediate, Scalable Object Category Detection." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.305

Markdown

[Aytar and Zisserman. "Immediate, Scalable Object Category Detection." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/aytar2014cvpr-immediate/) doi:10.1109/CVPR.2014.305

BibTeX

@inproceedings{aytar2014cvpr-immediate,
  title     = {{Immediate, Scalable Object Category Detection}},
  author    = {Aytar, Yusuf and Zisserman, Andrew},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.305},
  url       = {https://mlanthology.org/cvpr/2014/aytar2014cvpr-immediate/}
}