• Publications
  • Influence
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification
TLDR
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation. Expand
  • 153
  • 30
  • PDF
On the Performance of the MIMO Zero-Forcing Receiver in the Presence of Channel Estimation Error
TLDR
We investigate the effect of channel estimation error on the performance of MIMO ZF receivers in uncorrelated Rayleigh flat fading channels. Expand
  • 284
  • 25
  • PDF
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
TLDR
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. Expand
  • 63
  • 17
  • PDF
Approximate Nearest Neighbor Search by Residual Vector Quantization
TLDR
A recently proposed product quantization method is efficient for large scale approximate nearest neighbor search, however, its performance on unstructured vectors is limited. Expand
  • 83
  • 16
  • PDF
A novel extended local-binary-pattern operator for texture analysis
TLDR
The local-binary-pattern (LBP) operator has been proved to be a theoretically simple yet very effective multiresolution statistical texture descriptor in terms of the characteristics of the local structure, and has been applied in many areas. Expand
  • 172
  • 15
Energy-Sharing Model With Price-Based Demand Response for Microgrids of Peer-to-Peer Prosumers
TLDR
An energy-sharing model with price-based demand response is proposed for microgrids of peer-to-peer PV prosumers. Expand
  • 230
  • 15
Computation offloading to save energy on handheld devices: a partition scheme
TLDR
We consider handheld computing devices which are connected to a server (or a powerful desktop machine) via a wireless LAN. Expand
  • 322
  • 13
Separation of Ground and Low Vegetation Signatures in LiDAR Measurements of Salt-Marsh Environments
TLDR
We introduce reliable methods to remove random and systematic errors and to register raw data, as well as a new procedure, to determine the optimal filter window size to separate ground and canopy returns. Expand
  • 106
  • 12
  • PDF
Parametric analysis for adaptive computation offloading
  • C. Wang, Zhiyuan Li
  • Computer Science
  • PLDI '04
  • 9 June 2004
TLDR
We show how to use parametric program analysis to deal with this issue for the optimization problem of computation offloading. Expand
  • 116
  • 10
  • PDF
Robust high order discontinuous Galerkin schemes for two-dimensional gaseous detonations
TLDR
A simple solution for arbitrarily high order positivity-preserving schemes solving Euler equations was proposed recently in [22]. Expand
  • 92
  • 10
  • PDF