← Search

Wenqian Liu

2 accepted papers

2020

Towards Visually Explaining Variational Autoencoders

CVPR 2020oral

Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent effort in using visual attention maps as a means for visual…

Cited by 301PDFcodeScholar
2018

DYAN: A Dynamical Atoms-Based Network For Video Prediction

ECCV 2018poster

The ability to anticipate the future is essential when making real time critical decisions, provides valuable information to understand dynamic natural scenes, and can help unsupervised video representation learning. State-of-art video prediction is based on complex architectures that need to learn…

Cited by 39SourcePDFScholar