-
Article
Blind consumer video quality assessment with spatial-temporal perception and fusion
Blind quality assessment for user-generated content (UGC) or consumer videos is challenging in computer vision. Two open issues are yet to be addressed: how to effectively extract high-dimensional spatial-temp...
-
Chapter and Conference Paper
Pixel-Level Sonar Image JND Based on Inexact Supervised Learning
The Just Noticeable Difference (JND) model aims to identify perceptual redundancies in images by simulating the perception of the Human Visual System (HVS). Exploring the JND of sonar images is important for t...
-
Article
Virtual reality interaction based on visual attention and kinesthetic information
Emerging multimedia technologies significantly enhance the naturalness and immersion of human computer interaction. Currently, research on kinesthetic information has gained increasing attentions of multimedia...
-
Chapter and Conference Paper
Self-supervised Indoor 360-Degree Depth Estimation via Structural Regularization
Estimating \(360^{\circ }\) 360 ∘ ...
-
Article
An Optimized Segmentation Scheme for Ambiguous Pixels Based on Improved FCN and DenseNet
These past six years have witnessed that segmentation algorithms make a breakthrough due to the development of deep-based semantic segmentation networks, which can realize classification from image-level to pi...
-
Article
Multipath feature recalibration DenseNet for image classification
Recently, deep neural networks have demonstrated their efficiency in image classification tasks, which are commonly achieved by an extended depth and width of network architecture. However, poor convergence, o...
-
Chapter and Conference Paper
Video Playback Quality Evaluation Based on User Expectation and Memory
The Video Quality Assessment (VQA) has been attracting attentions of image processing community due to its applications in evaluation and optimization of user experience during video playback. Until now, the r...
-
Chapter and Conference Paper
QoE Assessment and Management of MV/3D Video Services
The measurements of Quality of Experience (QoE) are essential to research for better analysis and optimization of Multi-View and 3D (MV/3D) videos. However, there is a lack of systematic description of QoE mec...
-
Chapter and Conference Paper
Reconstruction of Multi-view Video Based on GAN
There is a huge amount of data in multi-view video which brings enormous challenges to the compression, storage, and transmission of video data. Transmitting part of the viewpoint information is a prior soluti...
-
Chapter and Conference Paper
Latitude-Based Visual Attention in 360-Degree Video Display
With the ever-growing availability of Virtual Reality (VR) products, the 360-degree video has a widespread application prospect, which also brings new challenges to its quality assessment. Considering its unco...
-
Article
Adaptive search range control in H.265/HEVC with error propagation resilience and hierarchical adjustment
In the state-of-the-art video coding standards H.26 4/AVC and H.265/HEVC, adaptive search range (ASR) control has achieved a significant performance in reducing the computational complexity of motion estimatio...
-
Article
Predictive and distribution-oriented fast motion estimation for H.264/AVC
For fast motion estimation (ME) in video coding, many fast block matching ME algorithms are proposed. Among these algorithms, Unsymmetrical-cross Multi-grid-hexagon Search (UMHexagonS) algorithm can be regarde...
-
Chapter and Conference Paper
Fast Mode Decision Based on Optimal Stop** Theory for Multiview Video Coding
Optimal stop** theory is developed to achieve a good trade-off between decision performance and decision efforts such as the consumed decision time. In this paper, the optimal stop** theory is applied to f...
-
Chapter and Conference Paper
Adaptive Rate-Distortion Prediction for Multiple Reference Selection and Inter-mode Decision
To minimize Rate-Distortion (RD) cost in video coding, RD Optimization (RDO) technique is adopted, which also brings increasingly computational complexity in Motion Estimation (ME), multiple reference selectio...
-
Chapter and Conference Paper
Fast Inter-Mode Decision Based on Rate-Distortion Cost Characteristics
In this paper, a new fast mode decision (FMD) algorithm is proposed for the state-of-the-art video coding standard H.264/AVC. Firstly, based on Rate-Distortion (RD) cost characteristics, all inter modes are cl...
-
Chapter and Conference Paper
Two-Dimensional Map Based Fast Mode Decision for H.264/AVC
The state-of-the-art video coding standard H.264/AVC achieves significant coding performance improvement by choosing the rate-distortion (RD) optimized encoding mode from a list of candidate modes at the cost ...
