Radu HORAUD
Author's posts
Jun 21
Welcome to New Permanent Member
The PERCEPTION team is pleased to announce that Xavier Alameda-PIneda has just been recruited as chargé de recherche at INRIA. Xavi will join the team next Fall. Currently, Xavi is a postdoc researcher at the University of Trento in the Multimedia and Human Understanding Group. Xavi’s webpage.
Jun 10
Deep Learning Reading Group
A deep learning reading group has started on June 2nd, jointly organized by the MISTIS, PERCEPTION and THOTH teams.
May 25
Matrix Completion: A Vision-oriented Perspective
Friday, June 3, 2016, 10:00 am to 11:00 am, room F107, INRIA Montbonnot Seminar by Xavier Alameda-Pineda, University of Trento, Italy Abstract: Matrix completion is a generic framework aiming to recover a matrix from a limited number of (possibly noisy) entries. In this context, low-rank regularizers are often imposed so as to find matrix estimators that are …
May 24
2016 Award for Outstanding Contributions in Neural Systems!
Antoine Deleforge (former team member, now with the PANAMA team, INRIA Bretagne-Atlantique), Florence Forbes (MISTIS team) and Radu Horaud received the 2016 Hojjat Adeli Award for Outstanding Contributions in Neural Systems for their paper: A. Deleforge, F. Forbes, and R. Horaud (2015), “Acoustic Space Learning for Sound-source Separation and Localization on Binaural Manifolds,” International Journal of Neural …
Mar 15
The AVDIAR Dataset
AVDIAR: A Dataset for Audio-Visual Diarization Publicly available dataset in conjunction with paper “Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion“ The AVDIAR dataset is only available for non-commercial use Citation Introduction Recording Setup Annotations Data Download Introduction AVDIAR (Audio-Visual Diarization) is a dataset dedicated to the audio-visual analysis of conversational scenes. Publicly available …
Mar 04
Guiding Robot Audition with Motor Data: A Hybrid Classifier-Dictionary Approach
Monday, March 7, 2016, 11:00 to 12:00, room F107, INRIA Montbonnot Seminar by Antoine Deleforge, PANAMA team, INRIA Rennes-Atlantique A specificity of human-robot interaction (HRI), as opposed to human-computer interaction (HCI), is the ability of a robot to perform movements. On the one hand, this ability may constitute an advantage, enabling active perception. On the …
Jan 05
Multi-task Learning for Activity Recognition and Event Detection, by Yan Yan
Monday, January 11, 2016, 2:30pm to 3:30pm, room F107, INRIA Montbonnot Seminar by Yan Yan, University of Trento, Italy Multiple Tasks are Better than One: Multi-task Learning for Head Pose Estimation, Activity Recognition and Event Detection Machine Learning (ML) and Computer Vision (CV) have been put together during the development of computer vision in the …
Nov 18
Multimodal head and body pose estimation, by Xavier Alameda-Pineda
Monday, November 23, 2015, 2:00pm to 3:00pm, room F107, INRIA Montbonnot Seminar by Xavier Alameda-Pineda, University of Trento, Italy Detecting social attention attractors in free-standing conversational groups through multimodal head and body pose estimation Abstract: During natural social gatherings, humans tend to organize themselves in the so-called free-standing conversational groups (FCGs). Studying FCGs in unstructured social settings …
Oct 30
ACM Multimedia 2015 Best Paper Award!
Xavier (Xavi) Alameda-Pineda, former Ph.D student in the PERCEPTION group (2010-2013) and his co-authors, Yan Yan (University of Trento, Italy), Elisa Ricci, Oswald Lanz (Fondazione Bruno Kessler, Italy), and Nicu Sebe (University of Trento, Italy), received the “Best Paper Award” at ACM MULTIMEDIA 2015 for the paper Analyzing Free-standing Conversational Groups: A Multimodal Approach. The conference took …
Oct 22
IEEE WASPAA’15: Best Student Paper Award!
Dionyssos Kounades-Bastian (PhD student) and his co-authors received the “Best Student Paper Award” at IEEE WASPAA’15 for the paper A Variational EM Algorithm for the Separation of Moving Sound Sources. The conference took place in New Paltz, NY, USA, October 2015. There were six papers nominated for the award, out of a total of 80 (oral and …
