#### Filter Results:

- Full text PDF available (16)

#### Publication Year

1963

2017

- This year (2)
- Last 5 years (15)
- Last 10 years (21)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Claire Morand, Jenny Benois-Pineau, Jean-Philippe Domenger, Joaquin Zepeda, Ewa Kijak, Christine Guillemot
- Sig. Proc.: Image Comm.
- 2010

- Joaquin Zepeda, Patrick Pérez
- 2015 IEEE Conference on Computer Vision and…
- 2015

In this work, we investigate the use of exemplar SVMs (linear SVMs trained with one positive example only and a vast collection of negative examples) as encoders that turn generic image features into new, task-tailored features. The proposed feature encoding leverages the ability of the exemplar-SVM (E-SVM) classifier to extract, from the original… (More)

The aggregation of image statistics – the so-called pooling step of image classification algorithms – as well as the construction of part-based models, are two distinct and well-studied topics in the literature. The former aims at leveraging a whole set of local descriptors that an image can contain (through spatial pyramids or Fisher vectors for instance)… (More)

This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it. To this end, we propose to approximate database vectors by constrained sparse coding, where possible atom weights are restricted to belong to a finite subset. This formulation encompasses, as particular cases, previous state-ofthe-art… (More)

- Joaquin Zepeda, Christine Guillemot, Ewa Kijak
- IEEE Journal of Selected Topics in Signal…
- 2011

We introduce a new image coder which uses the Iteration Tuned and Aligned Dictionary (ITAD) as a transform to code image blocks taken over a regular grid. We establish experimentally that the ITAD structure results in lower-complexity representations that enjoy greater sparsity when compared to other recent dictionary structures. We show that this superior… (More)

- Joaquin Zepeda, Christine Guillemot, Ewa Kijak
- 2011 IEEE International Conference on Acoustics…
- 2011

We present a new, block-based image codec based on sparse representations using a learned, structured dictionary called the Iteration-Tuned and Aligned Dictionary (ITAD). The question of selecting the number of atoms used in the representation of each image block is addressed with a new, global (image-wide), rate-distortion-based sparsity selection… (More)

- Joaquin Zepeda, Christine Guillemot, Ewa Kijak
- 2010 IEEE International Workshop on Multimedia…
- 2010

We introduce a new dictionary structure for sparse representations better adapted to pursuit algorithms used in practical scenarios. The new structure, which we call an Iteration-Tuned Dictionary (ITD), consists of a set of dictionaries each associated to a single iteration index of a pursuit algorithm. In this work we first adapt pursuit decompositions to… (More)

- Joaquin Zepeda, Ewa Kijak, Christine Guillemot
- 2009 IEEE International Workshop on Multimedia…
- 2009

This paper addresses the problem of efficient SIFT-based image description and searches in large databases within the framework of local querying. A descriptor called the bag-of-features has been introduced in [1] which first vector quantizes SIFT descriptors and then aggregates the set of resulting codeword indices (so-called visual words) into a histogram… (More)

We present a method that formulates the selection of the structure of a deep architecture as a penalized, discriminative learning problem. Up to now, the structure of deep architectures has been fixed by hand, and only the weights are learned using discriminative learning. Our work is a first attempt towards a more formal method of deep structure selection.… (More)

- Joaquin Zepeda, Ewa Kijak, Christine Guillemot
- 2010 IEEE International Conference on Acoustics…
- 2010

A new method is introduced that makes use of sparse image representations to search for approximate nearest neighbors (ANN) under the normalized inner-product distance. The approach relies on the construction of a new sparse vector designed to approximate the normalized inner-product between underlying signal vectors. The resulting ANN search algorithm… (More)