Institution
Hong Kong Polytechnic University
Education•Hong Kong, China•
About: Hong Kong Polytechnic University is a education organization based out in Hong Kong, China. It is known for research contribution in the topics: Tourism & Population. The organization has 29633 authors who have published 72136 publications receiving 1956312 citations. The organization is also known as: HKPU & PolyU.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: Experimental results demonstrate that the proposed local directional interpolation and nonlocal adaptive thresh- olding method outperforms many state-of-the-art CDM methods in reconstructing the edges and reducing color interpolation artifacts, leading to higher visual quality of reproduced color images.
Abstract: Single sensor digital color cameras capture only one of the three primary colors at each pixel and a process called color demosaicking (CDM) is used to reconstruct the full color images. Most CDM algorithms assume the existence of high local spectral redundancy in estimating the missing color samples. However, for images with sharp color transitions and high color saturation, such an assumption may be invalid and visually unpleasant CDM errors will occur. In this paper, we exploit the image nonlocal redundancy to improve the local color reproduction result. First, multiple local direc- tional estimates of a missing color sample are computed and fused according to local gradients. Then, nonlocal pixels similar to the esti- mated pixel are searched to enhance the local estimate. An adaptive thresholding method rather than the commonly used nonlocal means filtering is proposed to improve the local estimate. This allows the final reconstruction to be performed at the structural level as op- posed to the pixel level. Experimental results demonstrate that the proposed local directional interpolation and nonlocal adaptive thresh- olding method outperforms many state-of-the-art CDM methods in reconstructing the edges and reducing color interpolation artifacts, leading to higher visual quality of reproduced color images. © 2011
391 citations
••
TL;DR: A new dimensionality reduction algorithm is developed, termed discrim inative locality alignment (DLA), by imposing discriminative information in the part optimization stage, and thorough empirical studies demonstrate the effectiveness of DLA compared with representative dimensionality Reduction algorithms.
Abstract: Spectral analysis-based dimensionality reduction algorithms are important and have been popularly applied in data mining and computer vision applications. To date many algorithms have been developed, e.g., principal component analysis, locally linear embedding, Laplacian eigenmaps, and local tangent space alignment. All of these algorithms have been designed intuitively and pragmatically, i.e., on the basis of the experience and knowledge of experts for their own purposes. Therefore, it will be more informative to provide a systematic framework for understanding the common properties and intrinsic difference in different algorithms. In this paper, we propose such a framework, named "patch alignment,rdquo which consists of two stages: part optimization and whole alignment. The framework reveals that (1) algorithms are intrinsically different in the patch optimization stage and (2) all algorithms share an almost identical whole alignment stage. As an application of this framework, we develop a new dimensionality reduction algorithm, termed discriminative locality alignment (DLA), by imposing discriminative information in the part optimization stage. DLA can (1) attack the distribution nonlinearity of measurements; (2) preserve the discriminative ability; and (3) avoid the small-sample-size problem. Thorough empirical studies demonstrate the effectiveness of DLA compared with representative dimensionality reduction algorithms.
390 citations
••
TL;DR: In this article, the authors examined the impact of key supplier and customer integration processes (i.e., information sharing and product codevelopment with suppliers and customer, respectively) on product innovation as well as their impact on product performance.
390 citations
••
TL;DR: In this paper, a survey was conducted to evaluate three alternative waste sorting methods on building construction sites and to compare them with the use of an off-site central waste sorting facility, and the results indicated source separation has the advantages of requiring less effort and resulting in better segregation of inert and non-inert wastes as compared with waste sorting centrally carried out at a designated area on- or offsite.
Abstract: The construction industry is the major solid waste generator in Hong Kong. In 1998, it generated about 32 710 t per day of construction and demolition (C&D) waste. In the management of such a huge quantity of C&D waste, Hong Kong has adopted a strategy of depositing the inert portion (e.g. sand, bricks and concrete) of the waste at public filling areas for land reclamation and the non-inert portion (e.g. plastics, paper, wood) at municipal solid waste landfills. However, the C&D waste arisen is usually in the form of a mixture of both inert and non-inert materials. As a result, the waste has to be disposed of at landfills, aggravating the landfill shortage problem. There is a paramount need to separate the C&D waste into its constituent parts before it is delivered to either the landfills or the public filling areas for disposal. In order to study the feasibility of carrying out on-site waste sorting and the current situation of the building relating C&D waste generated in Hong Kong, a survey was conducted. This paper presents the results of the survey undertaken to evaluate three alternative waste sorting methods on building construction sites and to compare them with the use of an off-site central waste sorting facility. The results indicate source separation has the advantages of requiring less effort and resulting in better segregation of inert and non-inert wastes as compared with waste sorting centrally carried out at a designated area on- or off-site. In addition, the views of the building industry participants were also obtained through a questionnaire survey to give a better understanding of their attitude on on-site waste sorting. The results indicate that the building construction participants are reluctant to carry out on-site waste sorting. Even when high a tipping fee is imposed, they have little incentive to perform on-site waste sorting which is considered to be time and labour demanding. Only through contractual requirements or legislation can on-site waste sorting be fully implemented and becomes a long-term solution to the landfill shortage problem in Hong Kong.
389 citations
••
14 Jun 2020TL;DR: An auxiliary network is designed which converts the convolutional features in the backbone network back to point-level representations and an efficient part-sensitive warping operation is developed to align the confidences to the predicted bounding boxes.
Abstract: 3D object detection from point cloud data plays an essential role in autonomous driving. Current single-stage detectors are efficient by progressively downscaling the 3D point clouds in a fully convolutional manner. However, the downscaled features inevitably lose spatial information and cannot make full use of the structure information of 3D point cloud, degrading their localization precision. In this work, we propose to improve the localization precision of single-stage detectors by explicitly leveraging the structure information of 3D point cloud. Specifically, we design an auxiliary network which converts the convolutional features in the backbone network back to point-level representations. The auxiliary network is jointly optimized, by two point-level supervisions, to guide the convolutional features in the backbone network to be aware of the object structure. The auxiliary network can be detached after training and therefore introduces no extra computation in the inference stage. Besides, considering that single-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient part-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed detector ranks at the top of KITTI 3D/BEV detection leaderboards and runs at 25 FPS for inference.
389 citations
Authors
Showing all 30115 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jing Wang | 184 | 4046 | 202769 |
Xiang Zhang | 154 | 1733 | 117576 |
Wei Zheng | 151 | 1929 | 120209 |
Rui Zhang | 151 | 2625 | 107917 |
Jian Yang | 142 | 1818 | 111166 |
Joseph Lau | 140 | 1048 | 99305 |
Yu Huang | 136 | 1492 | 89209 |
Dacheng Tao | 133 | 1362 | 68263 |
Chuan He | 130 | 584 | 66438 |
Lei Zhang | 130 | 2312 | 86950 |
Ming-Hsuan Yang | 127 | 635 | 75091 |
Chao Zhang | 127 | 3119 | 84711 |
Yuri S. Kivshar | 126 | 1845 | 79415 |
Bin Wang | 126 | 2226 | 74364 |
Chi-Ming Che | 121 | 1305 | 62800 |