Sam Kwong

article

Deep sequential fusion LSTM network for image description

Pengjie Tang, Hanli Wang, Sam Kwong

Neurocomputing > 2018 > 312 > C > 154-164

It is a challenging task to perform automatic image description, which aims to translate an image with visual information into natural language conforming to certain proper grammars and sentence structures. In this work, an optimal learning framework called deep sequential fusion based long short term memory network is designed. In the proposed framework, a layer-wise strategy is introduced into the...

article

Quaternion representation based visual saliency for stereoscopic image quality assessment

Xu Wang, Lin Ma, Sam Kwong, Yu Zhou

Signal Processing > 2018 > 145 > C > 202-213

In this paper, a novel visual saliency detection method for stereoscopic images is proposed for the stereoscopic image quality assessment (SIQA) by considering the disparity map and difference image between the stereo image pairs. Firstly, a new quaternion representation (QR) of each stereo image (left/right view image) is constructed, which comprises the image content, the inter-view disparity, and...

article

CTU-Level Complexity Control for High Efficiency Video Coding

Jia Zhang, Sam Kwong, Tiesong Zhao, Zhaoqing Pan

IEEE Transactions on Multimedia > 2018 > 20 > 1 > 29 - 44

Among the existing video-related applications, a large proportion have requirements for the scalability of the video coding complexity, such as live video chatting and video coding on power-limited mobile devices. Hence, the complexity control algorithms, which aim to make an effective and flexible tradeoff between coding complexity and rate-distortion (RD) performance, have a great practical value...

article

Cooperative Bargaining Game-Based Multiuser Bandwidth Allocation for Dynamic Adaptive Streaming Over HTTP

Hui Yuan, Xuekai Wei, Fuzheng Yang, Jimin Xiao, more

IEEE Transactions on Multimedia > 2018 > 20 > 1 > 183 - 197

Dynamic adaptive streaming over HTTP (DASH) has emerged as an efficient technology for video streaming. For a DASH system, a most common case is that a limited server bandwidth is competed by multiusers. In order to improve user quality of experience (QoE) and guarantee fairness, we propose to use the game theory in a proxy server to allocate the bandwidth collaboratively for multiusers. By taking...

article

Joint Machine Learning and Game Theory for Rate Control in High Efficiency Video Coding

Wei Gao, Sam Kwong, Yuheng Jia

IEEE Transactions on Image Processing > 2017 > 26 > 12 > 6074 - 6089

In this paper, a joint machine learning and game theory modeling (MLGT) framework is proposed for inter frame coding tree unit (CTU) level bit allocation and rate control (RC) optimization in high efficiency video coding (HEVC). First, a support vector machine-based multi-classification scheme is proposed to improve the prediction accuracy of CTU-level rate-distortion (R-D) model. The legacy “chicken-and-egg”...

article

Incorporating Diversity and Informativeness in Multiple-Instance Active Learning

Ran Wang, Xi-Zhao Wang, Sam Kwong, Chen Xu

IEEE Transactions on Fuzzy Systems > 2017 > 25 > 6 > 1460 - 1475

Multiple-instance active learning (MIAL) is a paradigm to collect sufficient training bags for a multiple-instance learning (MIL) problem, by selecting and querying the most valuable unlabeled bags iteratively. Existing works on MIAL evaluate an unlabeled bag by its informativeness with regard to the current classifier, but neglect the internal distribution of its instances, which can reflect the...

article

Building Correlations Between Filters in Convolutional Neural Networks

Hanli Wang, Peiqiu Chen, Sam Kwong

IEEE Transactions on Cybernetics > 2017 > 47 > 10 > 3218 - 3229

In this paper, a new optimization approach is designed for convolutional neural network (CNN) which introduces explicit logical relations between filters in the convolutional layer. In a conventional CNN, the filters’ weights in convolutional layers are separately trained by their own residual errors, and the relations of these filters are not explored for learning. Different from the traditional...

article

Objective Video Quality Assessment Based on Perceptually Weighted Mean Squared Error

Sudeng Hu, Lina Jin, Hanli Wang, Yun Zhang, more

IEEE Transactions on Circuits and Systems for Video Technology > 2017 > 27 > 9 > 1844 - 1855

Object quality assessment for compressed video is critical to various video compression systems that are essential in the video delivery and storage. Although mean squared error (MSE) is computationally simple, it may not be accurate to reflect the perceptual quality of compressed videos, which are also affected dramatically by the characteristics of the human visual system (HVS), such as contrast...

article

Binary and Multi-Class Learning Based Low Complexity Optimization for HEVC Encoding

Linwei Zhu, Yun Zhang, Zhaoqing Pan, Ran Wang, more

IEEE Transactions on Broadcasting > 2017 > 63 > 3 > 547 - 561

High Efficiency Video Coding (HEVC) improves the compression efficiency at the cost of high computational complexity by using the quad-tree coding unit (CU) structure and variable prediction unit (PU) modes. To minimize the HEVC encoding complexity while maintaining its compression efficiency, a binary and multi-class support vector machine (SVM)-based fast HEVC encoding algorithm is presented in...

article

A Two-Phase Evolutionary Approach for Compressive Sensing Reconstruction

Yu Zhou, Sam Kwong, Hainan Guo, Xiao Zhang, more

IEEE Transactions on Cybernetics > 2017 > 47 > 9 > 2651 - 2663

Sparse signal reconstruction can be regarded as a problem of locating the nonzero entries of the signal. In presence of measurement noise, conventional methods such as

${l_{1}}$

norm relaxation methods and greedy algorithms, have shown their weakness in finding the nonzero entries accurately. In order to reduce the impact of noise and better locate the nonzero entries, in this paper, we propose...

article

Matching-Based Selection With Incomplete Lists for Decomposition Multiobjective Optimization

Mengyuan Wu, Ke Li, Sam Kwong, Yu Zhou, more

IEEE Transactions on Evolutionary Computation > 2017 > 21 > 4 > 554 - 568

The balance between convergence and diversity is the cornerstone of evolutionary multiobjective optimization (EMO). The recently proposed stable matching-based selection provides a new perspective to handle this balance under the framework of decomposition multiobjective optimization. In particular, the one-one stable matching between subproblems and solutions, which achieves an equilibrium between...

article

Motion-Homogeneous-Based Fast Transcoding Method From H.264/AVC to HEVC

Hui Yuan, Chenglin Guo, Ju Liu, Xu Wang, more

IEEE Transactions on Multimedia > 2017 > 19 > 7 > 1416 - 1430

With the popularity of high-efficiency video coding (HEVC) standard, a video server usually transcodes a video stream to HEVC for its higher compression ratio. In this paper, a fast H.264/advanced video coding (AVC) to HEVC transcoding method is proposed. In the HEVC encoding procedure, a coding unit (CU), which is a motion-homogeneous block, is first checked based on the analysis of the decoded information...

article

VideoSet: A large-scale compressed video quality dataset based on JND measurement

Haiqiang Wang, Ioannis Katsavounidis, Jiantong Zhou, Jeonghoon Park, more

Journal of Visual Communication and Image Representation > 2017 > 46 > C > 292-302

A new methodology to measure coded image/video quality using the just-noticeable-difference (JND) idea was proposed in Lin et al. (2015). Several small JND-based image/video quality datasets were released by the Media Communications Lab at the University of Southern California in Jin et al. (2016) and Wang et al. (2016) [3]. In this work, we present an effort to build a large-scale JND-based coded...

chapter

An efficient batch expensive multi-objective evolutionary algorithm based on Decomposition

Xi Lin, Qingfu Zhang, Sam Kwong

2017 IEEE Congress on Evolutionary Computation (CEC) > 1343 - 1349

2017 IEEE Congress on Evolutionary Computation (CEC)

This paper proposes a novel surrogate-model-based multi-objective evolutionary algorithm, which is called Multi-objective Bayesian Optimization Algorithm based on Decomposition (MOBO/D). In this algorithm, a multi-objective problem is decomposed into several subproblems which will be solved simultaneously. MOBO/D builds Gaussian process model for each objective to learn the optimization surface, and...

article

Spatial/temporal motion consistency based MERGE mode early decision for HEVC

Junaid Tariq, Sam Kwong, Hui Yuan

Journal of Visual Communication and Image Representation > 2017 > 44 > C > 198-213

A framework for the early decision of MERGE mode (EDM) is proposed to overcome the brute force inter mode decision for the coding unit (CU) in High Efficiency Video Coding (HEVC). Firstly, the prediction-results of merge candidates (MrgCands) in previous and current frame are modeled to identify smooth/single-motion regions for EDM. Secondly, the RD-cost based statistical model is proposed for EDM...

article

Fast Intra Prediction Based on Content Property Analysis for Low Complexity HEVC-Based Screen Content Coding

Jianjun Lei, Dongyang Li, Zhaoqing Pan, Zhenyan Sun, more

IEEE Transactions on Broadcasting > 2017 > 63 > 1-1 > 48 - 58

Screen content coding (SCC) has evolved into the extension of the High Efficiency Video Coding (HEVC). Low-latency, real-time transport between devices in the form of screen content video is becoming popular in many applications. However, the complexity of encoder is still very high for intra prediction in HEVC-based SCC. This paper proposes a fast intra prediction method based on content property...

article

G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition

Pengjie Tang, Hanli Wang, Sam Kwong

Neurocomputing > 2017 > 225 > C > 188-197

Scene recognition plays an important role in the task of visual information retrieval, segmentation and image/video understanding. Traditional approaches for scene recognition usually utilize handcrafted features and have the drawbacks of poor representation ability, which can be improved by employing deep convolutional neural network (CNN) features that contain more semantic and structure information...

article

High-Efficiency 3D Depth Coding Based on Perceptual Quality of Synthesized Video

Yun Zhang, Xiaoxiang Yang, Xiangkai Liu, Yongbing Zhang, more

IEEE Transactions on Image Processing > 2016 > 25 > 12 > 5877 - 5891

In 3D video systems, imperfect depth images often induce annoying temporal noise, e.g., flickering, to the synthesized video. However, the quality of synthesized view is usually measured with peak signal-to-noise ratio or mean squared error, which mainly focuses on pixelwise frame-by-frame distortion regardless of the obvious temporal artifacts. In this paper, a novel full reference synthesized video...

article

An efficient image segmentation method based on a hybrid particle swarm algorithm with learning strategy

Hao Gao, Chi-Man Pun, Sam Kwong

Information Sciences > 2016 > 369 > C > 500-521

Traditional threshold image segmentation method is a time consuming problem, we aim to find an effective optimal tool for proper threshold segmentation methods (e.g. Otsu and Kapur). In this work, we present a learning strategy based particle swarm optimization algorithm with an exchange method (LPSOWE). First, for enhancing the exploration ability and maintaining the convergence rate of the traditional...

chapter

Complex singular value decomposition based stereoscopic image quality assessment

Xu Wang, Lei Cao, Lin Ma, Yu Zhou, more

2016 Visual Communications and Image Processing (VCIP) > 1 - 4

2016 Visual Communications and Image Processing (VCIP)

Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. Due to the limited knowledge on 3D perceptual, it is difficult to fuse the visual information of left and right views in an effective way. In this paper, we propose a complex singular value decomposition (CSVD) based stereoscopic image quality assessment (SIQA) metric...

INFONA - science communication portal

Search results for: Sam Kwong

Deep sequential fusion LSTM network for image description

Quaternion representation based visual saliency for stereoscopic image quality assessment

CTU-Level Complexity Control for High Efficiency Video Coding

Cooperative Bargaining Game-Based Multiuser Bandwidth Allocation for Dynamic Adaptive Streaming Over HTTP

Joint Machine Learning and Game Theory for Rate Control in High Efficiency Video Coding

Incorporating Diversity and Informativeness in Multiple-Instance Active Learning

Building Correlations Between Filters in Convolutional Neural Networks

Objective Video Quality Assessment Based on Perceptually Weighted Mean Squared Error

Binary and Multi-Class Learning Based Low Complexity Optimization for HEVC Encoding

A Two-Phase Evolutionary Approach for Compressive Sensing Reconstruction

Matching-Based Selection With Incomplete Lists for Decomposition Multiobjective Optimization

Motion-Homogeneous-Based Fast Transcoding Method From H.264/AVC to HEVC

VideoSet: A large-scale compressed video quality dataset based on JND measurement

An efficient batch expensive multi-objective evolutionary algorithm based on Decomposition

Spatial/temporal motion consistency based MERGE mode early decision for HEVC

Fast Intra Prediction Based on Content Property Analysis for Low Complexity HEVC-Based Screen Content Coding

G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition

High-Efficiency 3D Depth Coding Based on Perceptual Quality of Synthesized Video

An efficient image segmentation method based on a hybrid particle swarm algorithm with learning strategy

Complex singular value decomposition based stereoscopic image quality assessment

Filter options

Publication date

Content availability

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Sam Kwong

Add recipient

Sending message cancelled

Are you sure you want to cancel sending this message?

Send message

Filter options

Publication date

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

Content availability

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options