• Publications
  • Influence
ContextVP: Fully Context-Aware Video Prediction
Video prediction models based on convolutional networks, recurrent networks, and their combinations often result in blurry predictions. We identify an important contributing factor for impreciseExpand
  • 54
  • 10
Short-Term Load Forecasting With Deep Residual Networks
We present in this paper a model for forecasting short-term electric load based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers’ understanding ofExpand
  • 78
  • 3
Domain Adaptive Transfer Learning for Fault Diagnosis
Thanks to digitization of industrial assets in fleets, the ambitious goal of transferring fault diagnosis models from one machine to the other has raised great interest. Solving these domain adaptiveExpand
  • 17
  • 2
Semi-Supervised Learning by Augmented Distribution Alignment
  • Qin Wang, W. Li, L. Gool
  • Computer Science, Mathematics
  • IEEE/CVF International Conference on Computer…
  • 20 May 2019
In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learningExpand
  • 10
  • 1
Convolutional Sequence to Sequence Non-intrusive Load Monitoring
A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences ofExpand
  • 16
Supplementary Material for Semi-Supervised Learning by Augmented Distribution Alignment
In this supplementary, we provide additional visualization results to demonstrate that our proposed Augmented Distribution Alignment is able to effectively address the impact by empiricalExpand
Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring
Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicatedExpand
  • 1