Aymen Shabou

Learn More
Improving coding and spatial pooling for bag-of-words based feature design have gained a lot of attention in recent works addressing object recognition and scene classification. Regarding the coding step in particular, properties such as sparsity, locality and saliency have been investigated. The main contribution of this work consists in taking into acount(More)
Markovian approaches have proven to be effective for solving the multichannel phase-unwrapping (PU) problem, particularly when dealing with noisy data and big discontinuities. This letter presents a Markovian approach to solve the PU problem based on a new a priori model, the total variation, and graph-cut-based optimization algorithms. The proposed method(More)
The IRIM group is a consortium of French teams working on Multimedia Indexing and Retrieval. This paper describes its participation to the TRECVID 2012 semantic indexing and instance search tasks. For the semantic indexing task, our approach uses a six-stages processing pipelines for computing scores for the likelihood of a video shot to contain a target(More)
The automatic attribution of semantic labels to unlabeled or weakly labeled images has received considerable attention but, given the complexity of the problem, remains a hard research topic. Here we propose a unified classification framework which mixes textual and visual information in a seamless manner. Unlike most recent previous works, computer vision(More)
This paper copes with the approximate minimization of Markovian energy with pairwise interactions. We extend previous approaches that rely on graph-cuts and move making techniques. For this purpose, a new move is introduced that permits us to perform better approximate optimizations. Some experiments show that very good local minima are obtained while(More)
Field inhomogeneities in Magnetic Resonance Imaging (MRI) can cause blur or image distortion as they produce off-resonance frequency at each voxel. These effects can be corrected if an accurate field map is available. Field maps can be estimated starting from the phase of multiple complex MRI data sets. In this paper we present a technique based on(More)
We introduce the bag-of-multimedia-words model that tightly combines the heterogeneous information coming from the text and the pixel-based information of a multimedia document. The proposed multimedia feature generation process is generic for any multimodality and aims at enriching a multimedia document description with compact and discriminative(More)
In this paper, a method to solve the multichannel phase unwrapping problem is presented. MAP approach together with Markov Random Fields have proved to be effective, allowing to restore the uniqueness of the solution without introducing external constraints to regularize the problem. The idea is to develop a fast algorithm to unwrap the interferometric(More)
This paper describes our participation to the ImageCLEF2012 Photo Annotation Task. We focus on how to use the tags associated to the images to improve the annotation performance. We submitted one textual-only and three multimodal runs. Our first textual model [14] is based on the local soft coding of images tags over a dictionary of most frequent tags. A(More)