Nonparametric estimation of fisher vectors to aggregate image descriptors

Authors:
Hervé Le Borgne;Pablo Muñoz Fuentes
Affiliations:
CEA, LIST, Laboratory of Vision and Content Engineering, Fontenay-au-Roses, France;CEA, LIST, Laboratory of Vision and Content Engineering, Fontenay-au-Roses, France
Venue:
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Year:
2011

Citing 10
Cited 0

Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Exploiting generative models in discriminative classifiers

Proceedings of the 1998 conference on Advances in neural information processing systems II
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Representation of images for classification with independent features

Pattern Recognition Letters
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
The visual concept detection task in ImageCLEF 2008

CLEF'08 Proceedings of the 9th Cross-language evaluation forum conference on Evaluating systems for multilingual and multimodal information access
Visual Word Ambiguity

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast shared boosting for large-scale concept detection

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate how to represent a natural image in order to be able to recognize the visual concepts within it. The core of the proposed method consists in a new approach to aggregate local features, based on a non-parametric estimation of the Fisher vector, that result from the derivation of the gradient of the loglikelihood. For this, we need to use low level local descriptors that are learned with independent component analysis and thus provide a statistically independent description of the images. The resulting signature has a very intuitive interpretation and we propose an efficient implementation as well. We show on publicly available datasets that the proposed image signature performs very well.