Publications depuis 2008

Vous pouvez retrouver les publications du laboratoire depuis 2008 sur le site des archives ouvertes du CNRS, et utiliser le moteur de recherche pour accéder à une publication particulière (onglets "Consultation" ou "Recherche simple").

Les publications des équipes depuis 2008 peuvent être également consultées à partir des liens suivants :

Publications antérieures à 2008

Les publications plus anciennes se trouvent à cette adresse.

10 most recent publications

[hal-02160704] Volumes of Blurred-Invariant Gaussians for Dynamic Texture Classification

An effective model, which jointly captures shape and motion cues, for dynamic texture (DT) description is introduced by taking into account advantages of volumes of blurred-invariant features in three main following stages. First, a 3-dimensional Gaussian kernel is used to form smoothed sequences that allow to deal with well-known limitations of local encoding such as near uniform regions and sensitivity to noise. [...]

[hal-02155055] Share - Publish - Store - Preserve. Methodologies, Tools and Challenges for 3D Use in Social Sciences and Humanities

Through this White Paper, which gathers contributions from experts of 3D data as well as professionals concerned with the interoperability and sustainability of 3D research data, the PARTHENOS project aims at highlighting some of the current issues they have to face, with possible specific points according to the discipline, and potential practices and methodologies to deal with these issues. [...]

[hal-02081474] RDF graph summarization: principles, techniques and applications (tutorial)

The explosion in the amount of the RDF on the Web has lead to the need to explore, query and understand such data sources. The task is challenging due to the complex and heterogeneous structure of RDF graphs which, unlike relational databases, do not come with a structure-dictating schema. [...]

[hal-02140049] Feature and structural learning of memory sequences with recurrent and gated spiking neural networks using free-energy: application to speech perception and production II

We present a framework based on iterative free-energy optimization with spiking neural network for modeling the fronto-striatal system (PFC-BG) for the generation and recall of audio memory sequences. In line with neuroimaging studies done in the PFC, we propose a genuine coding strategy using the gain-modulation mechanism to represent abstract sequences based on the rank and location of items within them only. [...]

[hal-02140046] Feature and structural learning of memory sequences with recurrent and gated spiking neural networks using free-energy: application to speech perception and production I

We propose a unified framework for modeling the cortico-basal system (CX-BG) and the fronto-striatal system (PFC-BG) for the generation and recall of audio memory sequences; ie, sound perception and speech production. Our genuine model is based on the neural architecture called INFERNO standing for Iterative Free-Energy Optimization of Recurrent Neural Networks. [...]

[hal-02073946] Brain-Inspired Coding of Robot Body Schema Through Visuo-Motor Integration of Touched Events

Representing objects in space is difficult because sensorimotor events are anchored in different reference frames, which can be either eye-, armor or target-centered. In the brain, Gain-Field (GF) neurons in the parietal cortex are involved in computing the necessary spatial transformations for aligning the tactile, visual and proprioceptive signals. [...]

[hal-01976669] Visual Learning for Reaching and Body-Schema with Gain-Field Networks

Perceiving our own body posture improves the way we move dynamically and reversely, motion coordination serves to learn better the position of our own body. Following this idea, we present a neural architecture toward reaching movements and body self-perception from a developmental perspective. [...]

[hal-02132416] Belief Propagation algorithm for Automatic Chord Estimation

This work aims at bridging the gap between two completely distinct research fields: digital communications and Music Information Retrieval. While works in the MIR community have long used algorithms borrowed from speech signal processing, text recognition or image processing, to our knowledge very scarce work based on digital communications algorithms has been produced. [...]

[hal-01993154] Tailoring Index-Modulation for uplink IoT and M2M Networks

The low complexity, low cost of implementation, as well as the spectral and energy efficiency, are key features for the development of the internet of things (IoT) networks. In this context, the introduction of index modulation on single carrier-frequency division multiple access (SC-FDMA-IM) has reported significant gains in terms of energy efficiency. [...]

[hal-02139747] Efficient Codebook and Factorization for Second Order Representation Learning

Learning rich and compact representations is an open topic in many fields such as object recognition or image retrieval. Deep neural networks have made a major breakthrough during the last few years for these tasks but their representations are not necessary as rich as needed nor as compact as expected. [...]