Yiu-ming Cheung

Yiu-ming Cheung
Hong Kong Baptist University · Department of Computer Science

PhD

About

371
Publications
36,794
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,241
Citations
Citations since 2017
124 Research Items
4039 Citations
20172018201920202021202220230200400600
20172018201920202021202220230200400600
20172018201920202021202220230200400600
20172018201920202021202220230200400600
Introduction
Skills and Expertise
Additional affiliations
September 2001 - present
Hong Kong Baptist University
Position
  • Professor (Full)

Publications

Publications (371)
Article
The scene classification of remote sensing (RS) images plays an essential role in the RS community, aiming to assign the semantics to different RS scenes. With the increase of spatial resolution of RS images, high-resolution RS (HRRS) image scene classification becomes a challenging task because the contents within HRRS images are diverse in type,...
Article
Recently, contrast enhancement with reversible data hiding (CE-RDH) has been proposed for digital images to hide useful data into contrast-enhanced images. In existing schemes, one-dimensional (1D) or two-dimensional (2D) histogram is equalized during the process of CE-RDH so that an original image can be exactly recovered from its contrast-enhance...
Article
Many constrained multiobjective evolutionary algorithms have been proposed in recent years. However, different regions of a multiobjective optimization problem may have different difficulties in meeting constraints, which leads to an unbalanced search on different regions. Currently, there is a lack of research in this area. Considering that differ...
Article
Despite the great success of the existing work in fine-grained visual categorization (FGVC), there are still several unsolved challenges, e.g., poor interpretation and vagueness contribution. To circumvent this drawback, motivated by the hypersphere embedding method, we propose a discriminative suprasphere embedding (DSE) framework, which can provi...
Article
Full-text available
Heterogeneous attribute data composed of attributes with different types of values are quite common in a variety of real-world applications. As data annotation is usually expensive, clustering has provided a promising way for processing unlabeled data, where the adopted similarity measure plays a key role in determining the clustering accuracy. How...
Article
For long-tailed distributed data, existing classification models often learn overwhelmingly on the head classes while ignoring the tail classes, resulting in poor generalization capability. To address this problem, we thereby propose a new approach in this paper, in which a key point sensitive (KPS) loss is presented to regularize the key points st...
Article
The class-imbalanced classification is a difficult problem because not only traditional classifiers are more biased towards the majority classes and inclined to generate incorrect predictions, but also the existing algorithms often have difficulty tackling this kind of problem with the class overlapping. Oversampling is a widely used and effective...
Article
Fine-grained image-text retrieval has been a hot research topic to bridge the vision and languages, and its main challenge is how to learn the semantic correspondence across different modalities. The existing methods mainly focus on learning the global semantic correspondence or intramodal relation correspondence in separate data representations, b...
Conference Paper
Full-text available
Data sets composed of a mixture of categorical and numerical attributes (also called mixed data hereinafter) are common in real-world cluster analysis. However, insightful analysis of such data under an unsupervised scenario using clustering is extremely challenging because the information provided by the two different types of attributes is hetero...
Preprint
Full-text available
Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex criterion to determine which components to be pruned. To this end, this paper presents a new method termed TissueNet, which directly constructs compact neural networks wit...
Article
Full-text available
Password guessing is an important issue in user security and privacy protection. Using generative adversarial network (GAN) to guess passwords is a new strategy emerging in recent years, which exploits the discriminator’s evaluation of passwords to guide the update of the generator so that password guessing sets can be produced. However, the sampli...
Article
Balancing convergence and diversity is a key issue for many-objective optimization problems (MaOPs), which is a great challenge to the classical Pareto-based multi-objective algorithms due to its severe lack of selection pressure. To relieve the above challenge, a Cα-dominance-based solution estimation evolutionary algorithm is proposed for MaOPs....
Preprint
The existing image retrieval approaches focus on the behavior of a single user only in each query without considering the correlation of the behaviors of multiple users in performing similar queries. In fact, users would have similar behaviors while they have similar expectations during queries. Accordingly, this paper therefore proposes the intera...
Preprint
Full-text available
Despite enormous research interest and rapid application of federated learning (FL) to various areas, existing studies mostly focus on supervised federated learning under the horizontally partitioned local dataset setting. This paper will study the unsupervised FL under the vertically partitioned dataset setting. Accordingly, we propose the federat...
Article
This work addresses unsupervised partial domain adaptation (PDA), in which classes in the target domain are a subset of the source domain. The key challenges of PDA are how to leverage source samples in the shared classes to promote positive transfer and filter out the irrelevant source samples to mitigate negative transfer. Existing PDA methods ba...
Article
Recent weakly supervised semantic segmentation methods generate pseudolabels to recover the lost position information in weak labels for training the segmentation network. Unfortunately, those pseudolabels often contain mislabeled regions and inaccurate boundaries due to the incomplete recovery of position information. It turns out that the result...
Article
Existing heterogeneous face synthesis (HFS) methods focus on performing accurate image-to-image translation across domains, while they cannot effectively remove the nuisance facial variations such as poses, expressions or occlusions. To address such challenges, this paper studies a new practical heterogeneous prototype learning (HPL) problem. To be...
Article
Cross-modal hashing has recently gained an increasing attention for its efficiency and fast retrieval speed in indexing the multimedia data across different modalities. Nevertheless, the multimedia data points often emerge in a streaming manner, which often makes the offline hashing methods loss their efficiency and flexibility. Besides, existing o...
Article
Reversible data hiding in ciphertext has potential applications for privacy protection and transmitting extra data in a cloud environment. For instance, an original plain-text image can be recovered from the encrypted image generated after data embedding, while the embedded data can be extracted before or after decryption. However, homomorphic proc...
Article
The robust reversible watermarking (RRW) requires high robustness and capacity on the condition of reversibility and imperceptibility, which still remains a big challenge nowadays. In this paper, we propose a two-stage RRW scheme that improves robustness and capacity through embedding optimization and rounded error compensation. The first stage ins...
Article
Parkinson's disease (PD) is a neurodegenerative disease which is prevalent among the elder population and severely affects the life quality of patients and their families. Therefore, it is important to conduct an early diagnosis for potential patients with PD, so as to promote prompt treatment and avoid the aggravation of the disease. Recently, the...
Article
With the explosive growth of the volume and resolution of high-resolution remote sensing (HRRS) images, the management of them becomes a challenging task. The traditional content-based remote sensing image retrieval (CBRSIR) technologies cannot meet what we expect due to the large volume of image archives and complex contents within HRRS images. As...
Article
Evolutionary sequential transfer optimization is a paradigm that leverages search experience from solved source optimization tasks to accelerate the evolutionary search of a target task. Even though many algorithms have been developed, they mainly focus on objective-homogeneous problems, where the source and target tasks possess a similar number of...
Article
It is a key issue to find out all longest common subsequences of multiple sequences over a set of finite alphabets, namely MLCS problem, in computational biology, pattern recognition and information retrieval, to name a few. However, it is very challenging to tackle the large-scale MLCS problem effectively and efficiently due to the high complexity...
Chapter
While position information plays a significant role in sentence scoring of single document summarization, the repetition of content among different documents greatly impacts the salience scores of sentences in multi-document summarization. Introducing frequencies information can help identify important sentences which are generally ignored when onl...
Article
Single sample per person face recognition (SSPP FR) is one of the most challenging problems in FR due to the extreme lack of enrolment data. To date, the most popular SSPP FR methods are the generic learning methods, which recognize query face images based on the so-called prototype plus variation (i.e., P+V) model. However, the classic P+V model s...
Article
Complete face recovering (CFR) is to recover the face image of a given partial face image of a target person whose photo may not be included in the gallery set. CFR has several attractive potential applications in surveillance, personal identification in forensics, to name a few, but it is challenging because of little information revealed from a s...
Article
This article presents a rough-to-fine evolutionary multiobjective optimization algorithm based on the decomposition for solving problems in which the solutions are initially far from the Pareto-optimal set. Subsequently, a tree is constructed by a modified $k$ -means algorithm on $N$ uniform weight vectors, and each node of the tree contains a...
Article
Ship detection plays a significant role in the high-resolution remote sensing (HRRS) community, but it is a challenging task due to the complex contents within HRRS images and the diverse orientation of ships. Recently, with the development of deep learning, the performance of the HRRS ship detection model has been improved greatly. Most of them em...
Article
Numerous surrogate-assisted expensive multi-objective optimization algorithms were proposed to deal with expensive multi-objective optimization problems in the past few years. The accuracy of the surrogate models degrades as the number of decision variables increases. In this paper, we propose a surrogate-assisted expensive multi-objective optimiza...
Preprint
Full-text available
Cross-modal hashing, favored for its effectiveness and efficiency, has received wide attention to facilitating efficient retrieval across different modalities. Nevertheless, most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes, while often involving time-consuming training p...
Article
Cross-modal hashing, favored for its effectiveness and efficiency, has received wide attention to facilitating efficient retrieval across different modalities. Nevertheless, most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes while often involving time-consuming training pr...
Article
Tensor singular value decomposition (t-SVD) has recently become increasingly popular for tensor recovery under partial and/or corrupted observations. However, the existing $t$ -SVD-based methods neither make use of a rank prior nor provide an accurate rank estimation (RE), which would limit their recovery performance. From the practical perspecti...
Article
The existing image retrieval methods generally require at least one complete image as a query sample. From the practical point of view, a user may not have an image sample in hand for query. Instead, partial information from multiple image samples would be available. This paper therefore attempts to deal with this problem by presenting a novel fram...
Article
Full-text available
Existing transfer learning methods that focus on problems in stationary environments are not usually applicable to dynamic environments, where concept drift may occur. To the best of our knowledge, the concept drift-tolerant transfer learning (CDTL), whose major challenge is the need to adapt the target model and knowledge of source domains to the...
Article
Full-text available
The success of categorical data clustering generally much relies on the distance metric that measures the dissimilarity degree between two objects. However, most of the existing clustering methods treat the two categorical subtypes, i.e. nominal and ordinal attributes, in the same way when calculating the dissimilarity without considering the relat...
Article
The papers in this special section focus on emerging computational intelligent techniques for decision making with Big Data in uncertain environments. Decision making in a big-data environment poses many challenges because of the high dimensional, heterogeneous, complex, unstructured, and unpredictable characteristics of the data which often suffer...
Article
Full-text available
Single sample per person (SSPP) face recognition with a contaminated biometric enrolment database (SSPP-ce FR) is an emerging practical FR problem, where the SSPP in the enrolment database is no longer standard but contaminated by nuisance facial variations such as expression, lighting, pose, and disguise. In this case, the conventional SSPP FR met...
Chapter
Despite the wide attention to federated learning (FL) in the literature, the existing studies mostly focus on supervised federated learning under the horizontally partitioned local dataset setting. This paper will study the unsupervised FL under the vertically partitioned dataset setting. Accordingly, we propose the vertically dataset partitioned f...
Article
Full-text available
With the popularity of cloud computing and social networks, more and more JPEG images are stored and distributed. Consequently, how to protect privacy and content in JPEG images has become an important issue. Although traditional encryption schemes can be employed, the file format of JPEG images is changed so that their usage may be affected. In th...
Article
In sparse empirical risk minimization (ERM) models, when sensitive personal data are used, e.g., genetic, healthcare, and financial data, it is crucial to preserve the differential privacy (DP) in training. In many applications, the information (i.e., features) of an individual is held by different organizations, which give rise to the prevalent ye...
Article
Due to the high dimensionality of hyperspectral images (HSIs), more training samples are needed in general for better classification performance. However, surface materials cannot always provide sufficient training samples in practice. HSI classification with small size training samples is still a challenging problem. Multiview learning is a feasib...
Article
In recent years, with the development of deep learning (DL), the hyperspectral image (HSI) classification methods based on DL have shown superior performance. Although these DL-based methods have great successes, there is still room to improve their ability to explore spatial-spectral information. In this article, we propose a 3-D octave convolutio...
Article
Cross-modal retrieval has received increasing attentions for efficient retrieval across different modalities, and hashing technique has made significant progress recently due to its low storage cost and high query speed. However, most existing cross-modal hashing works still face the challenges of narrowing down the semantic gap between different m...
Preprint
Complete face recovering (CFR) is to recover the complete face image of a given partial face image of a target person whose photo may not be included in the gallery set. The CFR has several attractive potential applications but is challenging. As far as we know, the CFR problem has yet to be explored in the literature. This paper therefore proposes...
Preprint
Complete face recovering (CFR) is to recover the complete face image of a given partial face image of a target person whose photo may not be included in the gallery set. The CFR has several attractive potential applications but is challenging. As far as we know, the CFR problem has yet to be explored in the literature. This paper therefore proposes...
Preprint
Facial sketch recognition is one of the most commonly used method to identify a suspect when only witnesses are available, which, however, usually leads to four gaps, i.e. memory gap, communication gap, description-sketch gap, and sketch-image gap. These gaps limit its application in practice to some extent. To circumvent these gaps, this paper the...
Preprint
Facial sketch recognition is one of the most commonly used method to identify a suspect when only witnesses are available, which, however, usually leads to four gaps, i.e. memory gap, communication gap, description-sketch gap, and sketch-image gap. These gaps limit its application in practice to some extent. To circumvent these gaps, this paper the...
Article
Full-text available
Ordinal attribute has all the common characteristics of a nominal one but it differs from the nominal one by having naturally ordered possible values (also called categories interchangeably). In clustering analysis tasks, categorical data composed of both ordinal and nominal attributes (also called mixed-categorical data interchangeably) are common...
Article
This article focuses on a new and practical problem in single-sample per person face recognition (SSPP FR), i.e., SSPP FR with a contaminated biometric enrolment database (SSPP-ce FR), where the SSPP-based enrolment database is contaminated by nuisance facial variations in the wild, such as poor lightings, expression change, and disguises (e.g., we...
Article
Full-text available
Clustering ordinal data is a common task in data mining and machine learning fields. As a major type of categorical data, ordinal data is composed of attributes with naturally ordered possible values (also called categories interchangeably in this paper). However, due to the lack of dedicated distance metric, ordinal categories are usually treated...
Article
Full-text available
Contrast enhancement (CE) of medical images is helpful to bring out the unclear content in the interested regions. Recently, reversible CE has been proposed so that the original version of a contrast-changed image can be exactly recovered. This property can be used to save storage space or facilitate the archiving system. To enhance the regions of...
Chapter
Recently, reversible data hiding in encrypted images (RDH-EI) has been developed to transmit additional data. Besides extracting the hidden data, the original or processed image should be obtained when needed. In this paper, a new RDH-EI method for homomorphic encrypted images is proposed by utilizing the additive homomorphism and self-blinding pro...
Article
One of the most challenging problems in the field of online learning is concept drift, which deeply influences the classification stability of streaming data. If the data stream is imbalanced, it is even more difficult to detect concept drifts and make an online learner adapt to them. Ensemble algorithms have been found effective for the classifica...
Article
Recent studies of imbalanced data classification have shown that the imbalance ratio (IR) is not the only cause of performance loss in a classifier, as other data factors, such as small disjuncts, noise, and overlapping, can also make the problem difficult. The relationship between the IR and other data factors has been demonstrated, but to the bes...
Preprint
The main feature of the Dynamic Multi-objective Optimization Problems (DMOPs) is that optimization objective functions will change with times or environments. One of the promising approaches for solving the DMOPs is reusing the obtained Pareto optimal set (POS) to train prediction models via machine learning approaches. In this paper, we train an I...
Article
Recently, based on a new tensor algebraic framework for third-order tensors, the tensor singular value decomposition (t-SVD) and its associated tubal rank definition have shed new light on low-rank tensor modeling. Its applications to robust image/video recovery and background modeling show promising performance due to its superior capability in mo...
Article
Full-text available
Recently, lossless contrast enhancement (CE) has been proposed so that a contrast-changed image can be converted to its original version by maintaining information entropy in it. As most of the lossless CE methods are proposed for grayscale images, artifacts are probably introduced after directly applying them to color images. For instance, color d...
Article
Hashing has recently sparked a great revolution in cross-modal retrieval because of its low storage cost and high query speed. Recent cross-modal hashing methods often learn unified or equal-length hash codes to represent the multi-modal data and make them intuitively comparable. However, such representations could inherently sacrifice their repres...
Article
Current unsupervised feature selection methods cannot well select the effective features from the corrupted data. To this end, we propose a robust unsupervised feature selection method under the robust principal component analysis (PCA) reconstruction criterion, which is named the adaptive weighted sparse PCA (AW-SPCA). In the proposed method, both...
Article
Recently, reversible image data hiding with contrast enhancement (CE) has been proposed so that a contrast-changed image can be converted to its original version when needed. Several reversible image CE methods have been proposed by adopting the technique of reversible data hiding (RDH) to embed the recovery information into the contrast-enhanced i...
Chapter
Large-scale global optimization (LSGO) problems are one of most difficult optimization problems and many works have been done for this kind of problems. However, the existing algorithms are usually not efficient enough for difficult LSGO problems. In this paper, we propose a new adaptive hybrid algorithm (NAHA) for LSGO problems, which integrates t...
Conference Paper
With the dramatic increase of multi-media data on the Internet, cross-modal retrieval has become an important and valuable task in searching systems. The key challenge of this task is how to build the correlation between multi-modal data. Most existing approaches only focus on dealing with paired data. They use pairwise relationship of multi-modal...
Article
Single sample per person face recognition (SSPP FR), i.e. identifying a person (i.e., data subject) with a single face image only for training, has several attractive potential applications, but is still a challenging problem. Existing generic learning methods usually leverage prototype plus variation (P+V) model for SSPP FR provided that face samp...
Article
Class imbalance problem has been extensively studied in the recent years, but imbalanced data clustering in unsupervised environment, that is, the number of samples among clusters is imbalanced, has yet to be well studied. This paper, therefore, studies the imbalanced data clustering problem within the framework of k-means-type competitive learning...
Article
We present an approach to extracting the salient object automatically in videos. Given an unannotated video sequence, the proposed method first computes the visual saliency to identify object-like regions in each frame based on the proposed weighted multiple manifold ranking algorithm. We then compute motion cues to estimate the motion saliency and...
Article
Subspace learning for tensors attracts increasing interest in recent years, leading to the development of multilinear extensions of principal component analysis (PCA) and probabilistic PCA (PPCA). Existing multilinear PPCAs are based on the Tucker or CANDECOMP/PARAFAC (CP) models. Although both kinds of multilinear PPCAs have shown their effectiven...
Article
Recently, reversible data hiding in encrypted images has been developed to transmit useful data while the original images can be perfectly recovered when needed. In this paper, a new method is proposed for homomorphic encrypted images so that part of the hidden data can be extracted in encrypted domain and the rest are extractable after image decry...
Article
Ordinal data are common in many data mining and machine learning tasks. Compared to nominal data, the possible values (also called categories interchangeably) of an ordinal attribute are naturally ordered. Nevertheless, since the data values are not quantitative, the distance between two categories of an ordinal attribute is generally not well defi...
Article
Hypervolume indicator based evolutionary algorithms have been reported to be very promising in many-objective optimization, but the high computational complexity of hypervolume calculation in high dimensions restrains its further applications and developments. In this paper, we develop a fast hypervolume approximation method with both improved spee...
Preprint
Recent studies have shown that imbalance ratio is not the only cause of the performance loss of a classifier in imbalanced data classification. In fact, other data factors, such as small disjuncts, noises and overlapping, also play the roles in tandem with imbalance ratio, which makes the problem difficult. Thus far, the empirical studies have demo...
Article
This paper proposes a high-capacity scheme for reversible data hiding (RDH) in encrypted images. The proposed scheme is based on a new preprocessing method by bit plane partition. Specifically, the values in the less significant bit planes are reversibly hidden into the other bit planes. Consequently, the room in the less significant bit planes can...
Article
Speaker naming has recently received considerable attention in identifying the active speaking character in a movie video, and face cue alone is generally insufficient to achieve reliable performance due to its significant appearance variations. In this paper, we treat the speaker naming task as a group of matched audio-face pair finding problems,...
Article
The key ingredients of matrix factorization lie in the basis learning and coefficient representation. To enhance the discriminant ability of the learnt basis, discriminant graph embedding is usually introduced in matrix factorization model. However, existing matrix factorization methods based on graph embedding generally conduct discriminant analys...