activity
20162025
most citedTime2Vec: Learning a Vector Representation of Time

51 citations · 98 across the 17 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

stat.CO20215 cited

Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals

James A. Brofos, Marylou Gabrié, Marcus A. Brubaker +1

Markov Chain Monte Carlo (MCMC) methods are a powerful tool for computation with complex probability distributions. However the performance of such methods is critically dependant…

cs.CV2021

Auto White-Balance Correction for Mixed-Illuminant Scenes

Mahmoud Afifi, Marcus A. Brubaker, Michael S. Brown

Auto white balance (AWB) is applied by camera hardware at capture time to remove the color cast caused by the scene illumination. The vast majority of white-balance algorithms assu…

cs.CV20212 cited

Zero-shot Learning with Class Description Regularization

Shayan Kousha, Marcus A. Brubaker

The purpose of generative Zero-shot learning (ZSL) is to learning from seen classes, transfer the learned knowledge, and create samples of unseen classes from the description of th…

cs.LG2021

Continuous Latent Process Flows

Ruizhi Deng, Marcus A. Brubaker, Greg Mori +1

Partial observations of continuous time-series dynamics at arbitrary time stamps exist in many disciplines. Fitting this type of data using statistical models with continuous dynam…

cs.CV2021

CAMS: Color-Aware Multi-Style Transfer

Mahmoud Afifi, Abdullah Abuolaim, Mostafa Hussien +2

Image style transfer aims to manipulate the appearance of a source image, or "content" image, to share similar texture and colors of a target "style" image. Ideally, the style tran…

stat.ML2021

Manifold Density Estimation via Generalized Dequantization

James A. Brofos, Marcus A. Brubaker, Roy R. Lederman

Density estimation is an important technique for characterizing distributions given observations. Much existing research on density estimation has focused on cases wherein the data…