• Publications
  • Influence
Mutations in SCN9A, encoding a sodium channel alpha subunit, in patients with primary erythermalgia
Primary erythermalgia is a rare autosomal dominant disease characterised by intermittent burning pain with redness and heat in the extremities. A previous study established the linkage of primaryExpand
  • 625
  • 34
  • PDF
Dynamic Network Embedding by Modeling Triadic Closure Process
TLDR
We present a novel representation learning approach, DynamicTriad, to preserve both structural information and evolution patterns of a given network. Expand
  • 177
  • 32
  • PDF
Reinforcement Learning for Relation Classification From Noisy Data
TLDR
In this paper, we propose a novel model for relation classification at the sentence level from noisy data. Expand
  • 177
  • 31
  • PDF
Energy-efficient dynamic offloading and resource scheduling in mobile cloud computing
TLDR
We propose a novel distributed eDors algorithm which is composed of three subalgorithms of computation offloading selection, clock frequency control and transmission power allocation. Expand
  • 193
  • 20
  • PDF
Remote Sensing of Irrigated Agriculture: Opportunities and Challenges
TLDR
We evaluate the state of the art of remote sensing-based monitoring of irrigated lands in several spectral regions. Expand
  • 174
  • 16
  • PDF
A Flicker-Free Electrolytic Capacitor-Less AC–DC LED Driver
The electrolytic capacitor is the key component that limits the operating lifetime of LED drivers. If an ac-dc LED driver with power factor correction (PFC) control is allowed to output a pulsatingExpand
  • 278
  • 14
  • PDF
Deep Learning Scaling is Predictable, Empirically
TLDR
This paper presents the largest scale empirical characterization of learning curves to date that reveals broadly that DL generalization error does show power-law improvement, but with exponents that must be predicted empirically. Expand
  • 163
  • 14
  • PDF
Scheduling divisible loads on star and tree networks: results and open problems
TLDR
We propose a unified theoretical perspective that synthesizes previously published results, several novel results, and open questions, in a view to foster new research directions in divisible load scheduling research. Expand
  • 150
  • 14
  • PDF
Embedding Deep Metric for Person Re-identification: A Study Against Large Variations
TLDR
We propose a novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation. Expand
  • 231
  • 13
  • PDF
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization
TLDR
We propose a simple yet effective unsupervised hashing framework, named Similarity-Adaptive Deep Hashing (SADH), which alternatingly proceeds over three training modules: deep hash model training, similarity graph updating and binary code optimization. Expand
  • 184
  • 10
  • PDF
...
1
2
3
4
5
...