Chun-Ho Cheung
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chun-Ho Cheung has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Lai-Man Po
City University of Hong Kong
14 shared publications Kwok-Wai Cheung
8 shared publicationsXuyuan Xu
7 shared publicationsLitong Feng
6 shared publicationsKa-Ho Ng
Department of Electronic Engineering, City University of Hong Kong, Hong Kong SAR, China
5 shared publicationsChi-Wang Ting
Department of Electronic Engineering, City University of Hong Kong, Hong Kong SAR, China
4 shared publications
Latest Publications
- Open Access
- 1 January 2017
- Published by HICSS Conference Office
Consumers' Sentiments and Popularity of Brand Posts in Social Media: The Moderating Role of Up-votes
User-generated contents (UGC) on online social media plays an important role in the branding and marketing of firms' products and services. In this study, we examine the effect of consumers' sentiments embedded in UGC on the popularity of brand posts. We retrieved real-world data from a social media platform and utilized a rigorous data analysis method that exploited state-of-the-art semi-supervised sentiment analysis technique. Our empirical findings confirm that positive and negative sentiments are associated with post popularity to some extent. Also, the customers' up-votes for negative comments somehow moderates the effect of negative comments on post popularity. To the best of our knowledge, this is the first study that demonstrates the specific role of upvotes in enhancing the popularity of brand posts on online social media. Our findings provide a promising theoretical contribution to the literature. The managerial implication is that firms can apply our findings to develop more effective strategies for marketing through social media brand communities.
- 1 January 2017
- Published by HICSS Conference Office
Open AccessConsumers' Sentiments and Popularity of Brand Posts in Social Media: The Moderating Role of Up-votes
User-generated contents (UGC) on online social media plays an important role in the branding and marketing of firms' products and services. In this study, we examine the effect of consumers' sentiments embedded in UGC on the popularity of brand posts. We retrieved real-world data from a social media platform and utilized a rigorous data analysis method that exploited state-of-the-art semi-supervised sentiment analysis technique. Our empirical findings confirm that positive and negative sentiments are associated with post popularity to some extent. Also, the customers' up-votes for negative comments somehow moderates the effect of negative comments on post popularity. To the best of our knowledge, this is the first study that demonstrates the specific role of upvotes in enhancing the popularity of brand posts on online social media. Our findings provide a promising theoretical contribution to the literature. The managerial implication is that firms can apply our findings to develop more effective strategies for marketing through social media brand communities.
- 1 April 2015
- Published by Elsevier in Neurocomputing
- Vol. 154, 94-109
No-reference image quality assessment with shearlet transform and deep neural networks
- 1 April 2015
- Published by Elsevier in Neurocomputing
- Vol. 154, 94-109
No-reference image quality assessment with shearlet transform and deep neural networks
- 1 January 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15301605,p. 1869-1878
Does Gender Make a Difference? Undergraduate Students' Use of Smart CVs for Career Planning
In the contemporary society, gender equality in accessing the job market is advocated, and often protected by law in developed countries. In reality, however, gender differences exist in different aspects and stages of recruitment processes and career development, say from career planning, job search, application, recruitment and promotion. Such differences are usually exemplified by different interesting findings in the literature. Some research findings had shown that male candidates spend less time than female candidates to secure a post-displacement job, male candidates in overall are more "linear" in job seeking than female candidates. One proposed explanation on the phenomenon is on how male and female candidates use online CVs for job hunting. This research aims to investigate the undergraduate students' perceived effects of three facets: Portfolio, Presentation and Presence in career planning, job search and application processes by using online CVs. Initial results indicate that gender differences exist on the perceptions of 3P's in career planning. Notably, female candidates see their Presence has direct relationship with Career Planning but male candidates do not. While male candidates perceive a direct relationship between Portfolio and Career Planning, but their female counterparts do not.
- 1 January 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15301605,p. 1869-1878
Does Gender Make a Difference? Undergraduate Students' Use of Smart CVs for Career Planning
In the contemporary society, gender equality in accessing the job market is advocated, and often protected by law in developed countries. In reality, however, gender differences exist in different aspects and stages of recruitment processes and career development, say from career planning, job search, application, recruitment and promotion. Such differences are usually exemplified by different interesting findings in the literature. Some research findings had shown that male candidates spend less time than female candidates to secure a post-displacement job, male candidates in overall are more "linear" in job seeking than female candidates. One proposed explanation on the phenomenon is on how male and female candidates use online CVs for job hunting. This research aims to investigate the undergraduate students' perceived effects of three facets: Portfolio, Presentation and Presence in career planning, job search and application processes by using online CVs. Initial results indicate that gender differences exist on the perceptions of 3P's in career planning. Notably, female candidates see their Presence has direct relationship with Career Planning but male candidates do not. While male candidates perceive a direct relationship between Portfolio and Career Planning, but their female counterparts do not.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 544-548
Adaptive block truncation filter for MVC depth image enhancement
In Multiview Video plus Depth (MVD) format, virtual views are generated from decoded texture videos with decoded depth images through Depth Image based Rendering (DIBR). 3DV-ATM is a reference model for H.264/AVC based Multiview Video Coding (MVC) and aims at achieving high coding efficiency for 3D video in MVD format. Depth images are first downsampled then coded by 3DV-ATM. However, sharp object boundary characteristic of depth images does not well match with the transform coding of 3DV-ATM. Depth boundaries are often blurred with ringing artifacts in the decoded depth images that result in noticeable artifacts in synthesized views. This paper presents a low complexity adaptive block truncation filter to recover the sharp object boundaries of depth images using adaptive block repositioning and expansion for increasing the depth values refinement accuracy. This new approach is very efficient and can avoid false depth boundary refinement when block boundaries lie around the depth edge regions and ensure sufficient information within the processing block for depth layers classification. Experimental results show that sharp depth edges can be recovered using the proposed filter and boundary artifacts in the synthesized views can be removed. The proposed method can provide improvement up to 3.25dB in the depth map enhancement and bitrate reduction of 3.06% in the synthesized views.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 544-548
Adaptive block truncation filter for MVC depth image enhancement
In Multiview Video plus Depth (MVD) format, virtual views are generated from decoded texture videos with decoded depth images through Depth Image based Rendering (DIBR). 3DV-ATM is a reference model for H.264/AVC based Multiview Video Coding (MVC) and aims at achieving high coding efficiency for 3D video in MVD format. Depth images are first downsampled then coded by 3DV-ATM. However, sharp object boundary characteristic of depth images does not well match with the transform coding of 3DV-ATM. Depth boundaries are often blurred with ringing artifacts in the decoded depth images that result in noticeable artifacts in synthesized views. This paper presents a low complexity adaptive block truncation filter to recover the sharp object boundaries of depth images using adaptive block repositioning and expansion for increasing the depth values refinement accuracy. This new approach is very efficient and can avoid false depth boundary refinement when block boundaries lie around the depth edge regions and ensure sufficient information within the processing block for depth layers classification. Experimental results show that sharp depth edges can be recovered using the proposed filter and boundary artifacts in the synthesized views can be removed. The proposed method can provide improvement up to 3.25dB in the depth map enhancement and bitrate reduction of 3.06% in the synthesized views.
- 1 March 2014
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 29 (3) , 316-331
Adaptive depth truncation filter for MVC based compressed depth image
- 1 March 2014
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 29 (3) , 316-331
Adaptive depth truncation filter for MVC based compressed depth image
- 1 November 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2366-2371
An adaptive background biased depth map hole-filling method for Kinect
The launch of Kinect provides a convenient way to access the depth information in real time. However the depth map quality still needs to be enhanced for 3D visual applications. In this paper, an adaptive background biased depth map hole-filling method is proposed. First, depth holes caused by abnormal reflection are filled by color similarity in-painting, and a soft decision for color similarity checking is performed by the use of probabilities in random walks color segmentation. Afterwards it is assumed that the lost information in the rest of depth holes belongs to the background. The background depth information is extracted by automatic thresholding in the neighborhood of each hole. Depth holes are in-painted with the background information in their local neighborhood. Combination of color similarity in-painting and background biased in-painting is able to perform depth map hole-filling adaptively for different kinds of depth holes for Kinect. The hole-filling results and virtual view synthesis results show that the Kinect depth map quality can be improved significantly by the proposed method.
- 1 November 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2366-2371
An adaptive background biased depth map hole-filling method for Kinect
The launch of Kinect provides a convenient way to access the depth information in real time. However the depth map quality still needs to be enhanced for 3D visual applications. In this paper, an adaptive background biased depth map hole-filling method is proposed. First, depth holes caused by abnormal reflection are filled by color similarity in-painting, and a soft decision for color similarity checking is performed by the use of probabilities in random walks color segmentation. Afterwards it is assumed that the lost information in the rest of depth holes belongs to the background. The background depth information is extracted by automatic thresholding in the neighborhood of each hole. Depth holes are in-painted with the background information in their local neighborhood. Combination of color similarity in-painting and background biased in-painting is able to perform depth map hole-filling adaptively for different kinds of depth holes for Kinect. The hole-filling results and virtual view synthesis results show that the Kinect depth map quality can be improved significantly by the proposed method.
- 1 October 2013
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 28 (9) , 1023-1045
Depth map misalignment correction and dilation for DIBR view synthesis
- 1 October 2013
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 28 (9) , 1023-1045
Depth map misalignment correction and dilation for DIBR view synthesis
- 13 September 2013
- Published by The Hong Kong Institution of Engineers in HKIE Transactions
- Vol. 20 (3) , 188-193
Radical-stroke-based Chinese input method using dynamic radical keypad on touchscreen smartphones
This paper presents a new Chinese input method that utilises finger gestures for improving stroke-based input method on touchscreen devices. It is a radical-stroke (RS) based method with a dynamic radical keypad (DRK), in which single radical multiple strokes coding is used. It speeds up the input of complex Chinese characters by simply sliding a finger. Experimental results show that the proposed RS–DRK outperforms the conventional Chinese input methods on an Android platform.
- 13 September 2013
- Published by The Hong Kong Institution of Engineers in HKIE Transactions
- Vol. 20 (3) , 188-193
Radical-stroke-based Chinese input method using dynamic radical keypad on touchscreen smartphones
This paper presents a new Chinese input method that utilises finger gestures for improving stroke-based input method on touchscreen devices. It is a radical-stroke (RS) based method with a dynamic radical keypad (DRK), in which single radical multiple strokes coding is used. It speeds up the input of complex Chinese characters by simply sliding a finger. Experimental results show that the proposed RS–DRK outperforms the conventional Chinese input methods on an Android platform.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 3152-3156
Watershed based depth map misalignment correction and foreground biased dilation for DIBR view synthesis
The quality of the synthesized views by Depth Image Based Rendering (DIBR) highly depends on the accuracy of the depth map, especially the alignment of object boundaries of texture image. In practice, the misalignment of sharp depth map edges is the major cause of the annoying artifacts at the disoccluded regions of the synthesized views. In this paper, a new depth map preprocessing method using Watershed misalignment correction and dilation filter is proposed to align the foreground depth edges to cover the whole transitional color edge regions. This approach can handle the sharp depth map edges lying inside or outside the object boundaries in 2D sense. The quality of the disoccluded regions of the synthesized views can be significantly improved. Experimental results show that the proposed method achieves superior performance for view synthesis by DIBR especially for generating large baseline virtual views.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 3152-3156
Watershed based depth map misalignment correction and foreground biased dilation for DIBR view synthesis
The quality of the synthesized views by Depth Image Based Rendering (DIBR) highly depends on the accuracy of the depth map, especially the alignment of object boundaries of texture image. In practice, the misalignment of sharp depth map edges is the major cause of the annoying artifacts at the disoccluded regions of the synthesized views. In this paper, a new depth map preprocessing method using Watershed misalignment correction and dilation filter is proposed to align the foreground depth edges to cover the whole transitional color edge regions. This approach can handle the sharp depth map edges lying inside or outside the object boundaries in 2D sense. The quality of the disoccluded regions of the synthesized views can be significantly improved. Experimental results show that the proposed method achieves superior performance for view synthesis by DIBR especially for generating large baseline virtual views.
- 1 May 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2840-2843
Depth-aided exemplar-based hole filling for DIBR view synthesis
Quality of synthesized view by Depth-Image-Based Rendering (DIBR) highly depends on hole filling, especially for synthesized view with large disocclusion. Many hole filling methods are proposed to improve the synthesized view quality and inpainting is the most popular approach to recover the disocclusions. However, the conventional inpainting either makes the hole regions blurred via diffusion or propagates the foreground information to the disoclusion regions. Annoying artifacts are created in the synthesized virtual views. This paper proposes a depth-aided exemplar-based inpainting method for recovering large disoclusion. It consists of two processes, warped depth map filling and warped color image filling. Since depth map can be considered as a grey-scale image without texture, it is much easier to be filled. Disoccluded regions of color image are predicted based on its associated filled depth map information. Regions with texture lying around the background have higher priority to be filled than other regions and disoccluded regions are filled by propagating the background texture through the exemplar-based inpainting. Thus artifacts created by diffusion or using foreground information for prediction can be eliminated. Experimental results show texture can be recovered in large disocclusions and the proposed method has better visual quality compared to existing methods.
- 1 May 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2840-2843
Depth-aided exemplar-based hole filling for DIBR view synthesis
Quality of synthesized view by Depth-Image-Based Rendering (DIBR) highly depends on hole filling, especially for synthesized view with large disocclusion. Many hole filling methods are proposed to improve the synthesized view quality and inpainting is the most popular approach to recover the disocclusions. However, the conventional inpainting either makes the hole regions blurred via diffusion or propagates the foreground information to the disoclusion regions. Annoying artifacts are created in the synthesized virtual views. This paper proposes a depth-aided exemplar-based inpainting method for recovering large disoclusion. It consists of two processes, warped depth map filling and warped color image filling. Since depth map can be considered as a grey-scale image without texture, it is much easier to be filled. Disoccluded regions of color image are predicted based on its associated filled depth map information. Regions with texture lying around the background have higher priority to be filled than other regions and disoccluded regions are filled by propagating the background texture through the exemplar-based inpainting. Thus artifacts created by diffusion or using foreground information for prediction can be eliminated. Experimental results show texture can be recovered in large disocclusions and the proposed method has better visual quality compared to existing methods.