The 2018 winner of the prestigious ACM Special Interest Group on Multimedia (SIGMM) Rising Star Award is our colleague Dr. Xavier Alameda-Pineda. The award is given in recognition of his contribution to multimodal social behavior understanding. Congratulations Xavi!
Category: News
Oct 10
(Closed) MSc. Project on Speaker identity modeling with deep learning for re-identification
MSc. Project on Speaker identity modeling with deep learning for re-identification Short description: Speaker identification is the task that aims at determining which speaker has produced a given utterance [1]. On the other hand, speaker verification or re-identification aims at determining whether there is a match between a given speech utterance and a target speaker …
Oct 10
(Closed) MSc. Project on Coupled Audio-visual Multi-speaker Tracking
MSc. Project on Coupled Audio-visual Multi-speaker Tracking Short description: Multi-speaker tracking has been widely investigated and the Perception team contributed with a consistent methodological framework based on variational Bayes techniques [1-4]. Often, audio-visual tracking methods first map all auditory and visual information in the same space, to later on run a tracking algorithm. However, in …
Oct 10
(Closed) MSc. Project on Gazeable Objects
MSc project on “Gazeable Objects” Duration: about 6 months Short description: Gaze is the direction towards which a person is looking. The automatic estimation of the gaze from a single image and from videos has been a hot research topic in previous years [1-4]. Often, researchers studied gaze from a human-centered perspective, trying to answer the …
Jun 15
Sparse representation, dictionary learning, and deep neural networks: their connections and new algorithms
Seminar by Mostafa Sadeghi, Sharif University of Technology, Tehran Tuesday 19 June 2018, 14:30 – 15:30, room F107 INRIA Montbonnot Saint-Martin Abstract. Over the last decade, sparse representation, dictionary learning, and deep artificial neural networks have dramatically impacted on the signal processing and machine learning areas by yielding state-of-the-art results in a variety of tasks, …
May 17
Deep Regression Models and Computer Vision Applications for Multiperson Human-Robot Interaction
PhD defense by Stéphane Lathuilière Tuesday 22nd May 2018, 11:00, Grand Amphithéatre INRIA Grenoble Rhône-Alpes, Montbonnot Saint-Martin Abstract: In order to interact with humans, robots need to perform basic perception tasks such as face detection, human pose estimation or speech recognition. However, in order have a natural interaction with humans, the robot needs to model …
Apr 09
Audio-Visual Analysis in the Framework of Humans Interacting with Robots
PhD defense by Israel D. Gebru Friday 13 April 2018, 9:30 – 10:30, Grand Amphithéatre INRIA Grenoble Rhône-Alpes, Montbonnot Saint-Martin In recent years, there has been a growing interest in human-robot interaction (HRI), with the aim to enable robots to naturally interact and communicate with humans. Natural interaction implies that robots not only need to …
Mar 31
Plane Extraction from Depth-Data
The following journal paper has just been published: Richard Marriott, Alexander Pashevich, and Radu Horaud. Plane Extraction from Depth Data Using a Gaussian Mixture Regression Model. Pattern Recognition Letters. vol. 110, pages 44-50, 2018. The paper is free for download from our publication page or directly from Elsevier.
Mar 29
(closed) Software engineer / Audio-visual perception for robotics
Context Perception team (https://team.inria.fr/perception), at INRIA Grenoble Rhône-Alpes and Jean Kuntzman Laboratory at Grenoble Alpes University, works on computational models for mapping images and sounds onto meaning and actions. The team members address these challenging topics: computer vision, auditory signal processing and scene analysis, machine learning, and robotics. In particular, we develop methods for the …
Dec 04
A Bayesian Framework for Head Pose Estimation and Tracking
PhD defense by Vincent Drouard Monday 18 December 2017, 11:00 – 12:00, Grand Amphithéatre INRIA Montbonnot Saint-Martin In this thesis, we address the well-known problem of head-pose estimation in the context of human-robot interaction (HRI). We accomplish this task in a two step approach. First, we focus on the estimation of the head pose from …