• Adversarial Recurrent Time Series Imputation 

      Shuo, Yang; Dong, Minjing; Wang, Yunhe; Xu, Chang
      Published 2020
      For the real-world time series analysis, data missing is a ubiquitously existing problem due to anomalies during data collecting and storage. If not treated properly, this problem will seriously hinder the classification, ...
      Open Access
      Article
    • Iterative Privileged Learning 

      Li, Xue; Du, Bo; Zhang, Yipeng; Xu, Chang; Tao, Dacheng
      Published 2020
      While in the learning using privileged information paradigm, privileged information may not be as informative as example features in the context of making accurate label predictions, it may be able to provide some effective ...
      Open Access
      Article
    • Long-Term Video Prediction via Criticization and Retrospection 

      Chen, Xinyuan; Xu, Chang; Yang, Xiaokang; Tao, Dacheng
      Published 2020
      Video prediction refers to predicting and generating future video frames given a set of consecutive frames. Conventional video prediction methods usually criticize the discrepancy between the ground-truth and predictions ...
      Open Access
      Article
    • Multi-task Learning for Blind Source Separation 

      Du, Bo; Wang, Shaodong; Xu, Chang; Wang, Nan; Zhang, Liangpei; Tao, Dacheng
      Published 2018
      Blind source separation (BSS) aims to discover the underlying source signals from a set of linear mixture signals without any prior information of the mixing system, which is a fundamental problem in signal and image ...
      Open Access
      Article
    • Packing Convolutional Neural Networks in the Frequency Domain 

      Wang, Yunhe; Xu, Chang; Xu, Chao; Tao, Dacheng
      Published 2019
      Deep convolutional neural networks (CNNs) are successfully used in a number of applications. However, their storage and computational requirements have largely prevented their widespread use on mobile devices. Here we ...
      Open Access
      Article
    • Robust learning with imperfect privileged information 

      Li, Xue; Du, Bo; Xu, Chang; Zhang, Yipeng; Zhang, Lefei; Tao, Dacheng
      Published 2020
      In the learning using privileged information (LUPI) paradigm, example data cannot always be clean, while the gathered privileged information can be imperfect in practice. Here, imperfect privileged information can refer ...
      Open Access
      Article
    • ROMIR: Robust Multi-view Image Re-ranking 

      Li, Jun; Xu, Chang; Yang, Wankou; Sun, Changyin; Kotagiri, Ramamohanarao; Tao, Dacheng
      Published 2019
      Recently, multi-view features have significantly pro- moted the performance of image re-ranking by providing complementary image descriptions. Without loss of generality, in multi-view re-ranking, multiple heterogeneous ...
      Open Access
      Article
    • Self-supervised Pose Adaptation for Cross-Domain Image Animation 

      Wang, Chaoyue; Xu, Chang; Tao, Dacheng
      Published 2020
      Image animation is to animate a still image of the object of interest using poses extracted from another video sequence. Through training on a large-scale video dataset, most existing approaches aim to explore disentangled ...
      Open Access
      Article