• Publications
  • Influence
High Performance Visual Tracking with Siamese Region Proposal Network
TLDR
In this paper, we propose the Siamese region proposal network (Siamese-RPN) which is end-to-end trained off-line with large-scale image pairs. Expand
  • 631
  • 183
  • PDF
SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
TLDR
Siamese network based trackers formulate tracking as convolutional feature cross-correlation between target template and searching region. Expand
  • 354
  • 134
  • PDF
PointCNN: Convolution On X-Transformed Points
TLDR
We present a simple and general framework for feature learning from point clouds by learning an Χ-transformation from the input points to simultaneously promote two causes: the first is the weighting of the input features associated with the points. Expand
  • 551
  • 98
  • PDF
Distractor-aware Siamese Networks for Visual Object Tracking
TLDR
In this paper, we focus on learning distractor-aware Siamese networks for accurate and long-term tracking. Expand
  • 372
  • 78
  • PDF
Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIs
TLDR
Canonical correlation analysis (CCA) is applied to analyze the frequency components of steady-state visual evoked potentials (SSVEP) in EEG. Expand
  • 450
  • 63
Feedback Network for Image Super-Resolution
TLDR
We propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Expand
  • 176
  • 49
  • PDF
Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs
TLDR
Canonical correlation analysis (CCA) is applied to analyze the frequency components of steady-state visual evoked potentials in electroencephalogram (EEG). Expand
  • 273
  • 46
  • PDF
Bayesian Population Decoding of Motor Cortical Activity Using a Kalman Filter
TLDR
We developed a real-time system that uses Bayesian inference techniques to estimate hand motion from the firing rates of multiple neurons. Expand
  • 418
  • 43
  • PDF
Improving cache lifetime reliability at ultra-low voltages
TLDR
We propose a novel adaptive technique to improve cache lifetime reliability and enable low voltage operation in the context of memory cell failure rates. Expand
  • 165
  • 31
  • PDF
SGM: Sequence Generation Model for Multi-label Classification
TLDR
We propose to view the multi-label classification task as a sequence generation problem, and apply a sequence Generation model with a novel decoder structure to solve it. Expand
  • 93
  • 28
  • PDF
...
1
2
3
4
5
...