Immediate, Scalable Object Category Detection

Yusuf Aytar, Andrew Zisserman; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 2377-2384

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Aytar_2014_CVPR,
author = {Aytar, Yusuf and Zisserman, Andrew},
title = {Immediate, Scalable Object Category Detection},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}
}