Decomposing Bag of Words Histograms

Ankit Gandhi 1 Karteek Alahari 2, 3, 4 C.V. Jawahar 1
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
4 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download
Contributor : Karteek Alahari <>
Submitted on : Friday, October 18, 2013 - 6:11:48 PM
Last modification on : Tuesday, March 12, 2019 - 5:20:03 PM
Long-term archiving on : Sunday, January 19, 2014 - 4:31:01 AM


Files produced by the author(s)




Ankit Gandhi, Karteek Alahari, C.V. Jawahar. Decomposing Bag of Words Histograms. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. pp.305-312, ⟨10.1109/ICCV.2013.45⟩. ⟨hal-00874895⟩



Record views


Files downloads