Search Results for author: Dominique Vaufreydaz

Found 12 papers, 2 papers with code

Preliminary Study on SSCF-derived Polar Coordinate for ASR

no code implementations30 Nov 2022 Sotheara Leang, Eric Castelli, Dominique Vaufreydaz, Sethserey Sam

According to the experimental results evaluated on the BRAF100 dataset, the polar coordinates achieved significantly higher accuracy than the angles in the mixed and cross-gender speech recognitions, demonstrating that these representations are superior at defining the acoustic trajectory of the speech signal.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Autoregressive GAN for Semantic Unconditional Head Motion Generation

1 code implementation2 Nov 2022 Louis Airale, Xavier Alameda-Pineda, Stéphane Lathuilière, Dominique Vaufreydaz

We address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space. Deviating from talking head generation conditioned on audio that seldom puts emphasis on realistic head motions, we devise a GAN-based architecture that allows obtaining rich head motion sequences while avoiding known caveats associated with GANs. Namely, the autoregressive generation of incremental outputs ensures smooth trajectories, while a multi-scale discriminator on input pairs drives generation toward better handling of high and low frequency signals and less mode collapse. We demonstrate experimentally the relevance of the proposed architecture and compare with models that showed state-of-the-art performances on similar tasks.

Talking Head Generation

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

1 code implementation CVPR 2022 Yangtao Wang, Xi Shen, Shell Hu, Yuan Yuan, James Crowley, Dominique Vaufreydaz

For unsupervised saliency detection, we improve IoU for 4. 9%, 5. 2%, 12. 9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art.

 Ranked #1 on Weakly-Supervised Object Localization on CUB-200-2011 (Top-1 Localization Accuracy metric)

object-detection Object Discovery +5

Navigation In Urban Environments Amongst Pedestrians Using Multi-Objective Deep Reinforcement Learning

no code implementations11 Oct 2021 Niranjan Deshpande, Dominique Vaufreydaz, Anne Spalanzani

Urban autonomous driving in the presence of pedestrians as vulnerable road users is still a challenging and less examined research problem.

Autonomous Driving Autonomous Navigation +3

SocialInteractionGAN: Multi-person Interaction Sequence Generation

no code implementations10 Mar 2021 Louis Airale, Dominique Vaufreydaz, Xavier Alameda-Pineda

In this paper, we focus on a unimodal representation of interactions and propose to tackle interaction generation in a data-driven fashion.

Behavioral decision-making for urban autonomous driving in the presence of pedestrians using Deep Recurrent Q-Network

no code implementations26 Oct 2020 Niranjan Deshpande, Dominique Vaufreydaz, Anne Spalanzani

In this work, a deep reinforcement learning based decision-making approach for high-level driving behavior is proposed for urban environments in the presence of pedestrians.

Autonomous Driving Decision Making +2

Group-Level Emotion Recognition Using a Unimodal Privacy-Safe Non-Individual Approach

no code implementations15 Sep 2020 Anastasia Petrova, Dominique Vaufreydaz, Philippe Dessus

This article presents our unimodal privacy-safe and non-individual proposal for the audio-video group emotion recognition subtask at the Emotion Recognition in the Wild (EmotiW) Challenge 2020 1.

Emotion Recognition

Deep learning investigation for chess player attention prediction using eye-tracking and game data

no code implementations17 Apr 2019 Justin Le Louedec, Thomas Guntz, James Crowley, Dominique Vaufreydaz

The visual attention model described in this article has been created to generate saliency maps that capture hierarchical and spatial features of chessboard, in order to predict the probability fixation for individual pixels Using a skip-layer architecture of an autoencoder, with a unified decoder, we are able to use multiscale features to predict saliency of part of the board at different scales, showing multiple relations between pieces.

Building Prior Knowledge: A Markov Based Pedestrian Prediction Model Using Urban Environmental Data

no code implementations17 Sep 2018 Pavan Vasishta, Dominique Vaufreydaz, Anne Spalanzani

Autonomous Vehicles navigating in urban areas have a need to understand and predict future pedestrian behavior for safer navigation.

Autonomous Vehicles

Multimodal Observation and Interpretation of Subjects Engaged in Problem Solving

no code implementations12 Oct 2017 Thomas Guntz, Raffaella Balzarini, Dominique Vaufreydaz, James L. Crowley

In this paper we present the first results of a pilot experiment in the capture and interpretation of multimodal signals of human experts engaged in solving challenging chess problems.

Starting engagement detection towards a companion robot using multimodal features

no code implementations12 Mar 2015 Dominique Vaufreydaz, Wafa Johal, Claudine Combe

Within the context of engagement, non-verbal signals are used to communicate the intention of starting the interaction with a partner.

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