YZYing Zhong

Ying Zhong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ying Zhong has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Knowledge Distillation Based Fast Degradation Estimator For Blind Super-resolution

    by Jian Lei, Ying Zhong, Xiao Feng Du

    Blind Super Resolution aims to enhance low-resolution images to high-resolution ones without the need to initially understand the detailed information of the original low-resolution images. In recent years, Blind Super Resolution techniques have attempted to guide image super-resolution reconstruction by designing explicit degradation estimators. However, these degradation estimators often come with a large number of parameters, slow processing speed, and less-than-ideal out-comes. In this study, we introduce an improved fast degradation estimator based on knowledge distillation, enabling the rapid and effective extraction of unknown degradation information from images. This estimator further guides the Super- Resolution(SR) network in achieving image super-resolution reconstruction. Ex-perimental results indicate that our enhanced fast degradation estimator doubles its operational efficiency and achieves super-resolution reconstruction for low-resolution images affected by various degradation factors. This advancement holds the promise of delivering superior performance and results for image super-resolution reconstruction tasks.


  • Deep Temporal Contrastive Clustering

    by Ying Zhong, Dong Huang, Chang-Dong Wang


  • Bilateral Privacy-Preserving Truthful Incentive for Mobile Crowdsensing

    by Ying Zhong, Xinglin Zhang

    Reverse auction-based incentive mechanisms have been widely adopted to stimulate mobile workers to participate in mobile crowdsensing (MCS), where workers need to provide location information for winner selection. However, most existing mechanisms rely on trusted platforms. The worker’s location data uploaded to platforms thus can be easily exposed. Recent works start to incorporate location privacy in designing incentive mechanisms, but they have not considered the task’s location privacy and the worker’s location privacy simultaneously. Therefore, we propose a bilateral location privacy-preserving mechanism for MCS on untrusted platforms. In our model, each worker adopts differential privacy to obfuscate his location locally and then submits the obfuscated location together with the bid information. Besides, instead of the exact location, the task requester is only required to upload the task profile and the task’s obfuscated location. Then, we propose the lowest-cost winner selection mechanism which aims to minimize the social cost of winner selection under the location constraint while ensuring task quality requirements, and adopt the critical payment determination mechanism to determine the payments for the winners, which satisfies truthfulness, individual rationality, and computational efficiency. Theoretical analysis and extensive experiments on real-world datasets show the effectiveness of the proposed mechanisms.


  • Open Access

    A System for Worldwide COVID-19 Information Aggregation

    by Akiko Aizawa, Frederic Bergeron, Junjie Chen, Fei Cheng, Katsuhiko Hayashi, Kentaro Inui, Hiroyoshi Ito, Daisuke Kawahara, Masaru Kitsuregawa, Hirokazu Kiyomaru, et al.

    The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education. Meanwhile, the COVID-19 condition is very different among the countries (e.g., policies and development of the epidemic), and thus citizens would be interested in news in foreign countries. We build a system for worldwide COVID-19 information aggregation containing reliable articles from 10 regions in 7 languages sorted by topics. Our reliable COVID-19 related website dataset collected through crowdsourcing ensures the quality of the articles. A neural machine translation module translates articles in other languages into Japanese and English. A BERT-based topic-classifier trained on our article-topic pair dataset helps users find their interested information efficiently by putting articles into different categories.

  • Study on Intelligent Extracting Algorithm of Fascicular Groups from Nerve Slice Image

    by Fang Li, Ying Chun Zhong, Jian Qi

    An intelligent algorithm is proposed to extract the fascicular groups regional image from the nerve slice image. First, some pixels in the original image are selected arbitarily and their gray level comatrix with different neighbourhood scale are calculated in order to establish the texture feature matrix. Second, the rough k-means is employed to cluster all the arbitarily selected pixels. The arbitarily selected pixels which are located in fascicular groups area would be classified in the same cluster. Then, the convex hull of those pixels located in fascicular groups is calculated in order to extract the regional image. The experiments show that the new proposal not only can be quick and accurate to extract the fascicular groups regional image but is independent on modifying the parameter while processing other nerve slice images, which reflects the new algorithm has good adaptability.

  • Perceptual quality of H.264/AVC deblocking filter

    by Y. Zhong, I. Richardson, A. Miller, Y. Zhao

    The H.264/AVC standard defines an optional in-loop deblocking filter. The effect of this filter on subjective video quality is investigated. Filter settings preferred by users are recorded for a group of 82 users across a range of video sequences and coded bitrates. The results indicate two clear groupings of user preferences for low- and medium-activity sequences. There is no clear user preference when the sequence contains high motion and activity. The implications of these results for performance optimisation of H264/AVC codecs are discussed.