• Publications
  • Influence
Robust Multiresolution Estimation of Parametric Motion Models
TLDR
We present two robust multiresolution algorithms for the estimation of parametric motion models. Expand
  • 711
  • 34
  • PDF
Modeling scenes with local descriptors and latent aspects
TLDR
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Expand
  • 443
  • 30
  • PDF
EYEDIAP: a database for the development and evaluation of gaze estimation algorithms from RGB and RGB-D cameras
TLDR
The lack of a common benchmark for the evaluation of gaze estimation task from RGB and RGB-D data is a serious limitation for distinguishing the advantages and disadvantages of the many proposed algorithms found in the literature. Expand
  • 136
  • 26
  • PDF
Multi-Layer Background Subtraction Based on Color and Texture
  • Jian Yao, J. Odobez
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 17 June 2007
TLDR
In this paper, we propose a robust multi-layer background subtraction technique which takes advantages of local texture features represented by local binary patterns (LBP) and photometric invariant color measurements in RGB color space. Expand
  • 278
  • 24
  • PDF
We are not contortionists: Coupled adaptive learning for head and body orientation estimation in surveillance video
  • C. Chen, J. Odobez
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 16 June 2012
TLDR
In this paper, we deal with the estimation of body and head poses (i.e orientations) in surveillance videos, and we make three main contributions. Expand
  • 86
  • 20
  • PDF
Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition
  • D. Wu, Lionel Pigou, +4 authors J. Odobez
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 August 2016
TLDR
A semi-supervised hierarchical dynamic framework based on a Hidden Markov Model (HMM) is proposed for simultaneous gesture segmentation and recognition where skeleton joint information, depth and RGB images, are the multimodal input observations. Expand
  • 262
  • 17
  • PDF
Text detection, recognition in images and video frames
TLDR
Text localization is performed in a two step approach that combines the speed of a focusing step with the strength of a machine learning based text verification step. Expand
  • 294
  • 15
  • PDF
Using particles to track varying numbers of interacting people
TLDR
In this paper, we present a Bayesian framework for the fully automatic tracking of a variable number of interacting targets using a fixed camera. Expand
  • 250
  • 13
  • PDF
Gaze estimation from multimodal Kinect data
  • K. Mora, J. Odobez
  • Computer Science
  • IEEE Computer Society Conference on Computer…
  • 16 June 2012
TLDR
This paper addresses the problem of free gaze estimation under unrestricted head motion. Expand
  • 117
  • 12
  • PDF
A Thousand Words in a Scene
TLDR
This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of textlike bag-of-visterms (BOV) representation and unsupervised latent space models. Expand
  • 216
  • 11
  • PDF