336 citations · 422 across the 13 of their papers we have counts for
10 papers · 1 filter
Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?
Koen P. de Vries, Xavier Alameda-Pineda, Estefanía Talavera +1
Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become t…
Diffusion Reinforcement Learning via Centered Reward Distillation
Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière +1
Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional corre…
Don't Forget your Inverse DDIM for Image Editing
Guillermo Gomez-Trenado, Pablo Mesejo, Oscar Cordón +1
The field of text-to-image generation has undergone significant advancements with the introduction of diffusion models. Nevertheless, the challenge of editing real images persists,…
Autoregressive GAN for Semantic Unconditional Head Motion Generation
Louis Airale, Xavier Alameda-Pineda, Stéphane Lathuilière +1
In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose. Different f…
Custom Structure Preservation in Face Aging
Guillermo Gomez-Trenado, Stéphane Lathuilière, Pablo Mesejo +1
In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image. We di…
Learning Visual Voice Activity Detection with an Automatically Annotated Dataset
Sylvain Guy, Stéphane Lathuilière, Pablo Mesejo +1
Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not. V-VAD is useful whenever audio VAD (A-VAD) is inefficient either becaus…
CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
Guillaume Delorme, Yihong Xu, Stephane Lathuilière +2
Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two tre…
Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of View
Benoit Massé, Stéphane Lathuilière, Pablo Mesejo +1
In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video.…
DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda +1
In this paper, we address the problem of how to robustly train a ConvNet for regression, or deep robust regression. Traditionally, deep regression employs the L2 loss function, kno…
A Comprehensive Analysis of Deep Regression
Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda +1
Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks. Vision tasks, such as human pos…