Category: Seminars

Acoustic Tracking of Moving Speakers, by Christine Evers

Monday, March 23, 2015, 3:00pm to 4:00pm, room C207, INRIA Montbonnot Seminar by Christine Evers, Imperial College, London   Localisation and bearing-only acoustic tracking of moving speakers for robot audition   Abstract. Robot audition for Human-Robot Interaction (HRI) is a complex and largely unsolved problem. Audition is particularly useful for HRI applications in situations where …

Continue reading

Deep Neural Networks and Speech Recognition, by Romain Sérizel

Thursday, February 12, 2015, 14:00 pm to 15:00 pm, room F107, INRIA Montbonnot Seminar by Romain Sérizel, Télécom ParisTech   A brief introduction to deep neural networks and their application to automatic speech recognition   Abstract. During the past decade, with advances in terms of training algorithms and computing power the deep neural networks (DNN) …

Continue reading

Model-Based Clustering Using Color and Depth Information, by Olivier Alata

Tuesday, October 14, 2014, 11:00 am to 12:00 am, room F107, INRIA Montbonnot Seminar by Olivier Alata, Université Jean Monnet, Saint-Etienne   Abstract. Access to the 3D images at a reasonable frame rate is widespread now, thanks to the recent advances in low cost depth sensors as well as the efficient methods to compute 3D …

Continue reading

Recent Advances in Human-centric Video Understanding, by Manuel-Jesus Marin-Jimenez

Thursday, March 20, 2014, 2:30 to 3:30 pm, room F107, INRIA Montbonnot Seminar by Manuel-Jesus Marin-Jimenez, University of Cordoba, Spain   In this seminar I will present recent advances in the field of visual content analysis focused on people. In particular, we are interested in understanding videos containing people-to-people interaction. Firstly, we will approach a …

Continue reading

Complex scene perception: contextual estimation of dynamic interacting variables, by Sileye Ba

Monday, January 13, 2014, 2:00 to 3:00 pm, room F107, INRIA Montbonnot Seminar by Sileye Ba, RN3D Innovation Lab, Marseille   During these last years researchers have conducted research about complex scene perception. Studying the perception scenes require modelling multiple interacting variables. Computer vision and machine learning have led to significant advances with models integrating multimodal observations …

Continue reading

Acoustic Space Mapping: A Machine Learning Approach to Sound Source Separation and Localization, by Antoine Deleforge

Tuesday, November 26, 2013, 10:00 to 10:45, Grand Amphi, INRIA Montbonnot PhD public defense by Antoine Deleforge, Perception Team, INRIA Montbonnot   Abstract: In this thesis, we address the long-studied problem of binaural (two microphones) sound source separation and localization through supervised learning. To achieve this, we develop a new paradigm referred as acoustic space mapping, …

Continue reading

Modelling via Mixtures of Skew Distributions, by Geoff McLachlan

Tuesday, November 26, 2013, 14:30 to 15:30, Grand Amphithéatre, INRIA Montbonnot Seminar by Geoff McLachlan, Department of Mathematics, University of Queensland, Australia   Abstract. Non-normal mixture distributions have received increasing attention in recent years. Finite mixtures of multivariate skew symmetric distributions, in particular, the skew normal and skew $t$-mixture models, are emerging as a promising extension to …

Continue reading

Visual Uncertainty: A Bayesian Approach, by Simon Barthelmé

Wednesday, November 13, 2013, 14:00 to 15:00, room F107, INRIA Montbonnot Seminar by Simon Barthelmé, Université de Genève   Abstract. Visual processing is fraught with uncertainty: the brain’s visual system must attempt to estimate physical properties despite missing information and noisy mechanisms. Sometimes high visual uncertainty translates into lack of confidence in our visual perception: we …

Continue reading

Egocentric Audio-Visual Scene Analysis, by Xavier Alameda-Pineda

Tuesday, October 15, 2013, 10:00 to 10:45, Grand Amphi, INRIA Montbonnot PhD public defense by Xavier Alameda-Pineda, Perception Team, INRIA Montbonnot Abstract. Along the past two decades, the industry has developed several commercial products with audio-visual sensingcapabilities. Most of them consists on a videocamera with an embedded microphone (mobile phones, tablets, etc). Other, such as Kinect, include …

Continue reading

The Future of Television, by Josep R. Casas

Tuesday, October 15, 2013, 2:00 to 3:00, room C207, INRIA Montbonnot by Josep Ramon Casas, Technical University of Catalonia (UPC), Barcelona Abstract.  Television, a telecommunication medium for the transmission of moving images and sound (cf.wikipedia). It substantiates the “far sight” concept of its mixed Greek-Latin etymology. But this definition may be misleading. Are the current technological solutions …

Continue reading