Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Home

Person

Jean-Marc Odobez

About
Privacy
Disclaimer

Graph Chatbot

Related publications (77)

Page 2 of 4

A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings

Samy Tafasca, Jean-Marc Odobez, Anshul Gupta

Predicting where a person is looking is a complex task, requiring to understand not only the person's gaze and scene content, but also the 3D scene structure and the person's situation (are they manipulating? interacting or observing others? attentive?) to ...

IEEE2022

Evaluating Shape Representations for Maya Glyph Classification

Daniel Gatica-Perez, Jean-Marc Odobez, Gülcan Can

Shape representations are critical for visual analysis of cultural heritage materials. This article studies two types of shape representations in a bag-of-words-based pipeline to recognize Maya glyphs. The first is a knowledge-driven Histogram of Orientati ...

Association for Computing Machinery2016

Deep Multitask Gaze Estimation with a Constrained Landmark-Gaze Model

Jean-Marc Odobez, Yu Yu

As an indicator of attention, gaze is an important cue for human behavior and social interaction analysis. Recent deep learning methods for gaze estimation rely on plain regression of the gaze from images without accounting for potential mismatches in eye ...

SPRINGER INTERNATIONAL PUBLISHING AG2018

Facing Employers and Customers: What Do Gaze and Expressions Tell About Soft Skills?

Daniel Gatica-Perez, Jean-Marc Odobez, Skanda Muralidhar, Rémy Alain Siegfried

Eye gaze and facial expressions are central to face-to-face social interactions. These behavioral cues and their connections to first impressions have been widely studied in psychology and computing literature, but limited to a single situation. Utilizing ...

ASSOC COMPUTING MACHINERY2018

Temporal Analysis of Motif Mixtures using Dirichlet Processes

Jean-Marc Odobez, Jagannadan Varadarajan

In this article, we present a new model for unsupervised discovery of recurrent temporal patterns (or motifs) in time series (or documents). The model is designed to handle the difficult case of multivariate time series obtained from a mixture of activitie ...

2014

Recognizing the Visual Focus of Attention for Human Robot Interaction

Jean-Marc Odobez, Samira Sheikhi

We address the recognition of people’s visual focus of attention (VFOA), the discrete version of gaze that indicates who is looking at whom or what. As a good indicator of addressee-hood (who speaks to whom, and in particular is a person speaking to the ro ...

Springer Berlin Heidelberg2012

Real-time Convolutional Networks for Depth-based Human Pose Estimation

Jean-Marc Odobez, Olivier Canévet, Michael Villamizar

We propose to combine recent Convolutional Neural Networks (CNN) models with depth imaging to obtain a reliable and fast multi-person pose estimation algorithm applicable to Human Robot Interaction (HRI) scenarios. Our hypothesis is that depth images conta ...

IEEE2018

Active Learning of Bayesian Probabilistic Movement Primitives

Jean-Marc Odobez, Sylvain Calinon, Hakan Girgin, Thibaut Antoine Kulak

Learning from Demonstration permits non-expert users to easily and intuitively reprogram robots. Among approaches embracing this paradigm, probabilistic movement primitives (ProMPs) are a well-established and widely used method to learn trajectory distribu ...

IEEE2021

ChildPlay-Hand: A Dataset of Hand Manipulations in the Wild

Jean-Marc Odobez, Samy Tafasca, Arya Farkhondeh

Hand-Object Interaction (HOI) is gaining significant attention, particularly with the creation of numerous egocentric datasets driven by AR/VR applications. However, third-person view HOI has received less attention, especially in terms of datasets. Most t ...

Springer Science and Business Media Deutschland GmbH2025

Learning Multimodal Temporal Representation for Dubbing Detection in Broadcast Media

Jean-Marc Odobez

Person discovery in the absence of prior identity knowledge requires accurate association of visual and auditory cues. In broadcast data, multimodal analysis faces additional challenges due to narrated voices over muted scenes or dubbing in different langu ...

ACM2016

Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization

Jean-Marc Odobez

Learning a good speaker embedding is critical for many speech processing tasks, including recognition, verification, and diarization. To this end, we propose a complementary optimizing goal called intra-class loss to improve deep speaker embed dings learne ...

ISCA-INT SPEECH COMMUNICATION ASSOC2018

Deep Neural Networks for Multiple Speaker Detection and Localization

Jean-Marc Odobez, Petr Motlicek, Weipeng He

We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction. In contrast to conventional signal processing techniques, neural network-based sound source localization methods require few ...

2018

Application of Information Retrieval Technologies to Presentation Slides

Jean-Marc Odobez, Alessandro Vinciarelli

Presentations are becoming an increasingly more common means of communication in working environments, and slides are often the necessary supporting material on which the presentations rely. In this paper, we describe a slide indexing and retrieval system ...

2006

Maya Codical Glyph Segmentation: A Crowdsourcing Approach

Daniel Gatica-Perez, Jean-Marc Odobez, Gülcan Can

This paper focuses on the crowd-annotation of an ancient Maya glyph dataset derived from the three ancient codices that survived up to date. More precisely, non-expert annotators are asked to segment glyph-blocks into their constituent glyph entities. As a ...

2018

Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis

Jean-Marc Odobez, Yu Yu

As an indicator of human attention gaze is a subtle behavioral cue which can be exploited in many applications. However, inferring 3D gaze direction is challenging even for deep neural networks given the lack of large amount of data (groundtruthing gaze is ...

IEEE2019

ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour

Jean-Marc Odobez, Anshul Gupta, Samy Tafasca

Gaze behaviors such as eye-contact or shared attention are important markers for diagnosing developmental disorders in children. While previous studies have looked at some of these elements, the analysis is usually performed on private datasets and is rest ...

Ieee Computer Soc2023

The MuMMER Data Set for Robot Perception in Multi-party HRI Scenarios

Jean-Marc Odobez, Petr Motlicek, Olivier Canévet

This paper presents the MuMMER data set, a data set for human-robot interaction scenarios that is available for research purposes% It comprises 1 h 29 min of multimodal recordings of people interacting with the social robot Pepper in entertainment scenario ...

IEEE2020

Towards the Use of Social Interaction Conventions as Prior for Gaze Model Adaptation

Jean-Marc Odobez, Yu Yu, Rémy Alain Siegfried

Gaze is an important non-verbal cue involved in many facets of social interactions like communication, attentiveness or attitudes. Nevertheless, extracting gaze directions visually and remotely usually suffers large errors because of low resolution images, ...

ACM2017

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers

Jean-Marc Odobez, Michael Villamizar

We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditioning on previous predictions such as in state-of-the-art RNN-based approach ...

IEEE COMPUTER SOC2021

Extracting Maya Glyphs from Degraded Ancient Documents via Image Segmentation

Daniel Gatica-Perez, Jean-Marc Odobez, Rui Hu

We present a system for automatically extracting hieroglyph strokes from images of degraded ancient Maya codices. Our system adopts a region-based image segmentation framework. Multi-resolution super-pixels are first extracted to represent each image. A Su ...

Association for Computing Machinery2017