Decomposing Bag of Words Histograms
Lists
Only you see this
Abstract
We aim to decompose a global histogram representation of an image into histograms of its associated objects and regions. This task is formulated as an optimization problem, given a set of linear classifiers, which can effectively discriminate the object categories present in the image. Our decomposition bypasses harder problems associated with accurately localizing and segmenting objects. We evaluate our method on a wide variety of composite histograms, and also compare it with MRF-based solutions. In addition to merely measuring the accuracy of decomposition, we also show the utility of the estimated object and background histograms for the task of image classification on the PASCAL VOC 2007 dataset.
BibTeX
@inproceedings{gandhi2013decomposing,
author = {Ankit Gandhi and Karteek Alahari and C. V. Jawahar},
title = {{Decomposing Bag of Words Histograms}},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2013},
doi = {10.1109/iccv.2013.45},
}| Object Classification with Adaptable Regions | CVPR · 2014 |
| Scene Classification Using Bag-of-Regions Representations | CVPR · 2007 |
| Learning component-level sparse representation using histogram information for image classification | ICCV · 2011 |
| Low-Rank Sparse Coding for Image Classification | ICCV · 2013 |
| Discriminating Semantic Visual Words for Scene Classification | IEICE Trans. Information and Systems · 2010 |
| Boosting Classifiers for Scene Category Recognition | J. Inf. Hiding Multim. Signal Process · 2015 |