Search Results for author:
Found 12 papers, 10 papers with code
Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis
Multiple Choice Learning is a simple framework to tackle multimodal density estimation, using the Winner-Takes-All (WTA) loss for a set of hypotheses.
DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion
We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively unexplored in 3D-HPE.
Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?
In this complex system, advances in conventional forecasting methods have been made using curated data, i. e., with the assumption of perfect maps, detection, and tracking.
Unifying GANs and Score-Based Diffusion as Generative Particle Models
Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance.
OCTET: Object-aware Counterfactual Explanations
We conduct a set of experiments on counterfactual explanation benchmarks for driving scenes, and we show that our method can be adapted beyond classification, e. g., to explain semantic segmentation models.
STEEX: Steering Counterfactual Explanations with Semantics
In this work, we address the problem of producing counterfactual explanations for high-quality images and complex scenes.
Raising context awareness in motion forecasting
Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history.
A Neural Tangent Kernel Perspective of GANs
We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs).
Stochastic Latent Residual Video Prediction
Designing video prediction models that account for the inherent uncertainty of the future is challenging.
Ranked #1 on
Video Prediction
on KTH 64x64 cond10 pred30
Unsupervised Object Segmentation by Redrawing
Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks.
Multi-View Data Generation Without View Supervision
We assume that the distribution of the data is driven by two independent latent factors: the content, which represents the intrinsic features of an object, and the view, which stands for the settings of a particular observation of that object.
Multi-view Generative Adversarial Networks
Most related studies focus on the classification point of view and assume that all the views are available at any time.
