Star-net: A spatial attention residue network for scene text recognition.

1 code implementation • The British Machine Vision Conference,2016 2016 • W. Liu, C. Chen, K.-Y. K. Wong, Z. Su, and J. Han.

Our STAR-Net is equipped with a spatial attention mechanism which employs a spatial transformer to remove the distortions of texts in natural images.

Optical Character Recognition (OCR) Scene Text Recognition

Multiview Hessian regularized logistic regression for action recognition

no code implementations • 3 Mar 2014 • W. Liu, H. Liu, D. Tao, Y. Wang, Ke Lu

With the rapid development of social media sharing, people often need to manage the growing volume of multimedia data such as large scale video classification and annotation, especially to organize those videos containing human activities.

Action Recognition Attribute +4

Large-Scale Paralleled Sparse Principal Component Analysis

no code implementations • 21 Dec 2013 • W. Liu, H. Zhang, D. Tao, Y. Wang, K. Lu

Principal component analysis (PCA) is a statistical technique commonly used in multivariate data analysis.

Manifold regularized kernel logistic regression for web image annotation

no code implementations • 21 Dec 2013 • W. Liu, H. Liu, D. Tao, Y. Wang, K. Lu

In this paper, we propose manifold regularized kernel logistic regression (KLR) for web image annotation.

Binary Classification regression