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
Journal ArticleDOI
Review on the preparation of high value-added carbon materials from biomass
TL;DR: In this paper , the authors summarized the preparation technologies of high value-added carbon materials (HVCMs) such as activated carbon, carbon nanotubes, carbon carbon nanofibers and graphene, and made an in-depth study on the raw material selection, preparation methods, reaction conditions and formation mechanism of biomass-based HVCMs.
Proceedings ArticleDOI
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
Zhaohui Yang,Yunhe Wang,Xinghao Chen,Jianyuan Guo,Wei Zhang,Chao Xu,Chunjing Xu,Dacheng Tao,Chang Xu +8 more
TL;DR: HourNAS as discussed by the authors proposes an hourglass-inspired approach for extremely fast neural architecture search, which is motivated by the fact that the effects of the architecture often proceed from the vital few blocks.
Proceedings ArticleDOI
GhostNetV2: Enhance Cheap Operation with Long-Range Attention
TL;DR: Wang et al. as discussed by the authors proposed a hardware-friendly attention mechanism (dubbed DFC attention) and then presented a new GhostNetV2 architecture for mobile applications, which can not only execute fast on common hardware but also capture the dependence between long-range pixels.
Proceedings ArticleDOI
Online reputation fraud campaign detection in user ratings
Chang Xu,Jie Zhang,Zhu Sun +2 more
TL;DR: This paper conducts RFC detection in online fashion, so as to spot campaign activities as early as possible, and proposes a unified and scalable optimization framework, FRAUDSCAN, that can adapt to emerging fraud patterns over time.
Journal ArticleDOI
Matrix Factorization for Collaborative Budget Allocation
Yaila Du,Chang Xu,Dacheng Tao +2 more
TL;DR: A matrix factorization framework is suggested to address the collaborative budget allocation problem by learning a group of a user profile as basis points that can be combined to recover other users’ rating vectors to enhance the robustness of collaborative prediction by relaxing the recovery constraint.