S
Shuai Zheng
Researcher at eBay
Publications - 56
Citations - 6449
Shuai Zheng is an academic researcher from eBay. The author has contributed to research in topics: Conditional random field & Convolutional neural network. The author has an hindex of 21, co-authored 55 publications receiving 5664 citations. Previous affiliations of Shuai Zheng include Oxford Brookes University & University of Oxford.
Papers
More filters
Proceedings ArticleDOI
Conditional Random Fields as Recurrent Neural Networks
Shuai Zheng,Sadeep Jayasumana,Bernardino Romera-Paredes,Vibhav Vineet,Zhizhong Su,Dalong Du,Chang Huang,Philip H. S. Torr +7 more
TL;DR: In this article, a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling is introduced.
Proceedings ArticleDOI
Conditional Random Fields as Recurrent Neural Networks
Shuai Zheng,Sadeep Jayasumana,Bernardino Romera-Paredes,Vibhav Vineet,Zhizhong Su,Dalong Du,Chang Huang,Philip H. S. Torr +7 more
TL;DR: A new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling is introduced, and top results are obtained on the challenging Pascal VOC 2012 segmentation benchmark.
Proceedings ArticleDOI
Efficient Salient Region Detection with Soft Image Abstraction
TL;DR: A novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation, which outperforms 18 alternate methods and is computationally more efficient.
Proceedings ArticleDOI
Robust view transformation model for gait recognition
TL;DR: Results show that the proposed method outperforms the other existing methods and brings the advantages that the view transformation model is robust to viewing angle variation, clothing and carrying condition changes.
Proceedings ArticleDOI
Fast End-to-End Trainable Guided Filter
TL;DR: Wu et al. as discussed by the authors proposed a guided filtering network, which can be expressed as a group of spatial varying linear transformation matrices and can be integrated with the convolutional neural networks and jointly optimized through end-to-end training.