• Publications
  • Influence
A Fast HEVC Inter CU Selection Method Based on Pyramid Motion Divergence
TLDR
In this paper, a fast pyramid motion divergence-based CU selection algorithm is presented for HEVC inter prediction. Expand
  • 198
  • 13
Waterloo Exploration Database: New Challenges for Image Quality Assessment Models
TLDR
The great content diversity of real-world digital images poses a grand challenge to image quality assessment (IQA) models, which are traditionally designed and validated on a handful of commonly used IQA databases with very limited content variation. Expand
  • 135
  • 10
  • PDF
A highly efficient method for blind image quality assessment
  • Q. Wu, Z. Wang, H. Li
  • Computer Science
  • IEEE International Conference on Image Processing…
  • 10 December 2015
TLDR
We propose a novel BIQA method by selecting statistical features extracted from binary patterns of local image structures. Expand
  • 62
  • 8
  • PDF
Group MAD Competition? A New Methodology to Compare Objective Image Quality Models
  • K. Ma, Q. Wu, +4 authors Lei Zhang
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 1 June 2016
TLDR
We first build a database that contains 4,744 source natural images, together with 94,880 distorted images created from them. Expand
  • 53
  • 7
  • PDF
Workflow scheduling in cloud: a survey
TLDR
In this paper, we firstly conduct taxonomy and comparative review on workflow scheduling algorithms. Expand
  • 133
  • 6
Blind Image Quality Assessment Based on Multichannel Feature Fusion and Label Transfer
  • Q. Wu, H. Li, +4 authors B. Zeng
  • Computer Science
  • IEEE Transactions on Circuits and Systems for…
  • 1 March 2016
TLDR
In this paper, we propose an efficient blind image quality assessment (BIQA) algorithm, which is characterized by a feature fusion scheme and a k-nearest-neighbor (KNN)-based quality prediction model. Expand
  • 105
  • 5
  • PDF
LETRIST: Locally Encoded Transform Feature Histogram for Rotation-Invariant Texture Classification
TLDR
This paper proposes a simple yet effective image descriptor, called Locally Encoded TRansform feature hISTogram (LETRIST), for texture classification. Expand
  • 60
  • 5
Noise-Robust Texture Description Using Local Contrast Patterns via Global Measures
TLDR
This letter presents a noise-robust descriptor by exploring a set of local contrast patterns (LCPs) via global measures for texture classification in the presence of high levels of noise. Expand
  • 48
  • 5
  • PDF
MRF-Based Fast HEVC Inter CU Decision With the Variance of Absolute Differences
TLDR
The newly developed High Efficiency Video Coding (HEVC) Standard has improved video coding performance significantly in comparison to its predecessors. Expand
  • 54
  • 4
Key-Word-Aware Network for Referring Expression Image Segmentation
TLDR
We propose a key-word-aware network (KWAN) that extracts key words for each image region and models the key- word-aware visual context among multiple image regions in accordance with the natural language query. Expand
  • 28
  • 4
  • PDF