Search Results for author: Jean-Marc Odobez

Found 15 papers, 5 papers with code

An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning

1 code implementation2 Aug 2021 Marco Ewerton, Angel Martínez-González, Jean-Marc Odobez

In this paper, we propose to frame the learning of pushing policies (where to push and how) by DQNs as an image-to-image translation problem and exploit an Hourglass-based architecture.

Image-to-Image Translation Translation

Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation

1 code implementation10 Nov 2020 Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez

We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction (HRI) scenarios.

3D Human Pose Estimation 3D Pose Estimation

IEEE SLT 2021 Alpha-mini Speech Challenge: Open Datasets, Tracks, Rules and Baselines

1 code implementation4 Nov 2020 Yihui Fu, Zhuoyuan Yao, Weipeng He, Jian Wu, Xiong Wang, Zhanheng Yang, Shimin Zhang, Lei Xie, DongYan Huang, Hui Bu, Petr Motlicek, Jean-Marc Odobez

In this challenge, we open source a sizable speech, keyword, echo and noise corpus for promoting data-driven methods, particularly deep-learning approaches on KWS and SSL.

Sound Audio and Speech Processing

Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation

no code implementations2 Dec 2019 Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez

i) we study several CNN architecture designs combining pose machines relying on the cascade of detectors concept with lightweight and efficient CNN structures; ii) to address the need for large training datasets with high variability, we rely on semi-synthetic data combining multi-person synthetic depth data with real sensor backgrounds; iii) we explore domain adaptation techniques to address the performance gap introduced by testing on real depth images; iv) to increase the accuracy of our fast lightweight CNN models, we investigate knowledge distillation at several architecture levels which effectively enhance performance.

Domain Adaptation Knowledge Distillation +1

Unsupervised Representation Learning for Gaze Estimation

no code implementations CVPR 2020 Yu Yu, Jean-Marc Odobez

Although automatic gaze estimation is very important to a large variety of application areas, it is difficult to train accurate and robust gaze models, in great part due to the difficulty in collecting large and diverse data (annotating 3D gaze is expensive and existing datasets use different setups).

Gaze Estimation gaze redirection +2

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

no code implementations30 Oct 2019 Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez

(i) we propose a fast and efficient network based on residual blocks (called RPM) for body landmark localization from depth images; (ii) we created a public dataset DIH comprising more than 170k synthetic images of human bodies with various shapes and viewpoints as well as real (annotated) data for evaluation; (iii) we show that our model trained on synthetic data from scratch can perform well on real data, obtaining similar results to larger models initialized with pre-trained networks.

Human Detection Multi-Person Pose Estimation

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

no code implementations CVPR 2019 Yu Yu, Gang Liu, Jean-Marc Odobez

In this work, we address the problem of person-specific gaze model adaptation from only a few reference training samples.

Domain Adaptation Gaze Estimation +1

A Differential Approach for Gaze Estimation

no code implementations20 Apr 2019 Gang Liu, Yu Yu, Kenneth A. Funes Mora, Jean-Marc Odobez

Non-invasive gaze estimation methods usually regress gaze directions directly from a single face or eye image.

Gaze Estimation

Theoretical Guarantees of Deep Embedding Losses Under Label Noise

no code implementations6 Dec 2018 Nam Le, Jean-Marc Odobez

Collecting labeled data to train deep neural networks is costly and even impractical for many tasks.

Deep Neural Networks for Multiple Speaker Detection and Localization

1 code implementation30 Nov 2017 Weipeng He, Petr Motlicek, Jean-Marc Odobez

We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction.

Improving speaker turn embedding by crossmodal transfer learning from face embedding

no code implementations10 Jul 2017 Nam Le, Jean-Marc Odobez

Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail.

Face Verification Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.