Search Results for author: Jérémie Mary

Found 14 papers, 4 papers with code

Lessons from the AdKDD'21 Privacy-Preserving ML Challenge

no code implementations31 Jan 2022 Eustache Diemert, Romain Fabre, Alexandre Gilotte, Fei Jia, Basile Leparmentier, Jérémie Mary, Zhonghua Qu, Ugo Tanielian, Hui Yang

Designing data sharing mechanisms providing performance and strong privacy guarantees is a hot topic for the Online Advertising industry.

EdiBERT, a generative model for image editing

1 code implementation30 Nov 2021 Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard

Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks.

Image Denoising Image Manipulation

Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On

no code implementations ECCV 2020 Thibaut Issenhuth, Jérémie Mary, Clément Calauzènes

This task requires fitting an in-shop cloth image on the image of a person, which is highly challenging because it involves cloth warping, image compositing, and synthesizing.

Image Generation Virtual Try-on

Distributionally Robust Reinforcement Learning

no code implementations23 Feb 2019 Elena Smirnova, Elvis Dohmatob, Jérémie Mary

Our formulation results in a efficient algorithm that accounts for a simple re-weighting of policy actions in the standard policy iteration scheme.

Continuous Control Q-Learning +1

Visual Reasoning with Multi-hop Feature Modulation

1 code implementation ECCV 2018 Florian Strub, Mathieu Seurin, Ethan Perez, Harm de Vries, Jérémie Mary, Philippe Preux, Aaron Courville, Olivier Pietquin

Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue.

Question Answering Visual Dialog +2

Recurrent Neural Networks for Long and Short-Term Sequential Recommendation

no code implementations23 Jul 2018 Kiewan Villatel, Elena Smirnova, Jérémie Mary, Philippe Preux

Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon.

Dimensionality Reduction Sequential Recommendation +1

Multi-Task Determinantal Point Processes for Recommendation

no code implementations24 May 2018 Romain Warlop, Jérémie Mary, Mike Gartrell

Determinantal point processes (DPPs) have received significant attention in the recent years as an elegant model for a variety of machine learning tasks, due to their ability to elegantly model set diversity and item quality or popularity.

General Classification Multi-class Classification +2

Hybrid Recommender System based on Autoencoders

4 code implementations24 Jun 2016 Florian Strub, Romaric Gaudel, Jérémie Mary

A standard model for Recommender Systems is the Matrix Completion setting: given partially known matrix of ratings given by users (rows) to items (columns), infer the unknown ratings.

Collaborative Filtering Matrix Completion +1

Bandits Warm-up Cold Recommender Systems

no code implementations10 Jul 2014 Jérémie Mary, Romaric Gaudel, Preux Philippe

Finally, experimental evidence confirm that our algorithm is effective in dealing with the cold start problem on publicly available datasets.

Multi-Armed Bandits Recommendation Systems

Reducing statistical time-series problems to binary classification

no code implementations NeurIPS 2012 Daniil Ryabko, Jérémie Mary

The algorithms that we construct for solving these problems are based on a new metric between time-series distributions, which can be evaluated using binary classification methods.

Classification General Classification +2

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