C
Chang Xu
Researcher at University of Sydney
Publications - 467
Citations - 13012
Chang Xu is an academic researcher from University of Sydney. The author has contributed to research in topics: Computer science & Chemistry. The author has an hindex of 42, co-authored 260 publications receiving 7189 citations. Previous affiliations of Chang Xu include University of Melbourne & Information Technology University.
Papers
More filters
Book ChapterDOI
PowerLSTM: Power Demand Forecasting Using Long Short-Term Memory Neural Network
TL;DR: This paper proposes PowerLSTM, a power demand forecasting model based on Long Short-Term Memory (L STM) neural network, and calculates the feature significance and compact the authors' model by capturing the features with the most important weights.
Journal ArticleDOI
Discriminative Multi-View Interactive Image Re-Ranking
TL;DR: This paper proposes a discriminative multi-view interactive image re-ranking (DMINTIR), which integrates user relevance feedback capturing users’ intentions and multiple features that sufficiently describe the images.
Proceedings Article
Vector-valued multi-view semi-supervised learning for multi-label image classification
TL;DR: The proposed multi-view vector-valued manifoldRegularization (MV3MR) exploits the complementary properties of different features, and discovers the intrinsic local geometry of the compact support shared by different features under the theme of manifold regularization.
Posted Content
ReNAS:Relativistic Evaluation of Neural Architecture Search
TL;DR: This paper proposes a relativistic architecture performance predictor in NAS (ReNAS), encoding neural architectures into feature tensors, and further refining the representations with the predictor, to determine which architecture would perform better instead of accurately predict the absolute architecture performance.
Proceedings ArticleDOI
Towards Collusive Fraud Detection in Online Reviews
TL;DR: A novel statistical model is proposed to further characterize, recognize, and forecast collusive fraud in online reviews and is completely unsupervised, which bypasses the difficulty of manual annotation required for supervised modeling.