research
∙
07/08/2021
Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation
Attention is a general reasoning mechanism than can flexibly deal with i...
share
research
∙
01/28/2021
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
In this work, we propose TimeGrad, an autoregressive model for multivari...
research
∙
06/09/2020
CRISP: A Probabilistic Model for Individual-Level COVID-19 Infection Risk Estimation Based on Contact Data
We present CRISP (COVID-19 Risk Score Prediction), a probabilistic graph...
research
∙
02/14/2020
Multi-variate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
Time series forecasting is often fundamental to scientific and engineeri...
research
∙
09/06/2019
Set Flow: A Permutation Invariant Normalizing Flow
We present a generative model that is defined on finite sets of exchange...
research
∙
08/23/2019
Generating High-Resolution Fashion Model Images Wearing Custom Outfits
Visualizing an outfit is an essential part of shopping for clothes. Due ...
research
∙
07/23/2019
A Deep Learning System for Predicting Size and Fit in Fashion E-Commerce
Personalized size and fit recommendations bear crucial significance for ...
research
∙
06/22/2019
Learning Set-equivariant Functions with SWARM Mappings
In this work we propose a new neural network architecture that efficient...
research
∙
02/10/2019
A Bandit Framework for Optimal Selection of Reinforcement Learning Agents
Deep Reinforcement Learning has been shown to be very successful in comp...
research
∙
07/02/2018
Studio2Shop: from studio photo shoots to fashion articles
Fashion is an increasingly important topic in computer vision, in partic...
research
∙
03/02/2018
Syntax-Aware Language Modeling with Recurrent Neural Networks
Neural language models (LMs) are typically trained using only lexical fe...
research
∙
08/25/2017
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale im...
research
∙
08/24/2017
An LSTM-Based Dynamic Customer Model for Fashion Recommendation
Online fashion sales present a challenging use case for personalized rec...
research
∙
05/18/2017
Learning Texture Manifolds with the Periodic Spatial GAN
This paper introduces a novel approach to texture synthesis based on gen...
research
∙
11/24/2016