Haoran Xie

Haoran Xie
Lingnan University · Department of Computing and Decision Sciences

BEng, MSc, PhD (Computer Science) and EdD (Digital Learning), SrMACM, SrMIEEE

About

325
Publications
94,192
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
7,016
Citations
Additional affiliations
July 2020 - present
Elsevier
Position
  • Editor-in-Chief
January 2020 - present
Lingnan University
Position
  • Professor (Associate)
July 2016 - January 2020
The Education University of Hong Kong
Position
  • Professor (Assistant)

Publications

Publications (325)
Article
Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we pro...
Article
In this study, the trends and developments of technology-enhanced adaptive/personalized learning have been studied by reviewing the related journal articles in the recent decade (i.e., from 2007 to 2017). To be specific, we investigated many research issues such as the parameters of adaptive/personalized learning, learning supports, learning outcom...
Article
Sentiment strength detection is an essential task in sentiment analysis, wherein the sentiment strength of subjective text is automatically determined. Sentiment analysis has numerous applications in different sectors, including business and social domains. In this study, we present a model to effectively extract the features and strength of sentim...
Article
Personalized recommendation systems have solved the information overload problem caused by large volumes of Web data effectively. However, most existing recommendation algorithms are weak in handling the problem of rating data sparsity that characterizes most recommender systems and results in deteriorated recommendation accuracy. The results in th...
Article
Full-text available
Brain informatics is a novel interdisciplinary area that focuses on scientifically studying the mechanisms of human brain information processing by integrating experimental cognitive neuroscience with advanced Web intelligence-centered information technologies. Web intelligence, which aims to understand the computational, cognitive, physical, and s...
Article
Full-text available
Image decomposition is a useful operation that benefits a number of low-level vision tasks. However, this conventional wisdom is not well studied in deep learning, and almost no existing deep learning-based methods consider the fact that the extracted feature map from a convolution layer consists of different frequency information. We propose an en...
Article
Full-text available
As an important task in Asian language information processing, Chinese word embedding learning has attracted much attention recently. Based on either Skip-gram or CBOW, several methods have been proposed to exploit Chinese characters and sub-character components for learning Chinese word embeddings. Chinese characters are combinations of meaning, s...
Article
Using deep learning to automatically and quickly extract faults from seismic images is of practical significance. An improved U-Net algorithm is proposed by reducing convolutional layers, designing skip connections, enforcing deep supervision, and improving the loss function and learning rate to build a new model. In the operation, the feature map...
Article
Full-text available
Secure deduplication aims to efficiently eliminate redundant data in cloud storage system, where convergent encryption (CE) is widely-used to provide the data confidentiality. As the number of convergent keys (CKs) in CE will increase dramatically with enlarging data, there is a critical issue that how to safely manage the CKs. Previous works usual...
Preprint
How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, and then refine its local details. We are motivated to imitate the physical repair procedure to address point cloud completion. To this end, we propose a cross-modal shape...
Article
Full-text available
The diversity and advance of information, communication, and analytical technologies and their increasing adoption to assist instruction and learning give rise to various technology-driven conferences (e.g., artificial intelligence in education) in educational technology. Previous reviews on educational technology commonly focused on journal articl...
Article
Massive open online courses (MOOCs) have exploded in popularity; course reviews are important sources for exploring learners’ perceptions about different factors associated with course design and implementation. This study aims to investigate the possibility of automatic classification for the semantic content of MOOC course reviews to understand f...
Preprint
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most of existing methods still suffer from either the object-level misclassification or the boundary-level ambiguity. In this paper, we present a robust semantic segmentation...
Article
Full-text available
The application of artificial intelligence (AI) technologies in assisting human electroencephalogram (EEG) analysis has become an active scientific field. This study aims to present a comprehensive review of the research field of AI-enhanced human EEG analysis. Using bibliometrics and topic modeling, research articles concerning AI-enhanced human E...
Article
Can you find me? By simulating how humans to discover the so-called 'perfectly'-camouflaged object, we present a novel boundary-guided separated attention network (call BSA-Net). Beyond the existing camouflaged object detection (COD) wisdom, BSA-Net utilizes two-stream separated attention modules to highlight the separator (or say the camouflaged o...
Article
Understanding vasculatures is important for endovascular intervention simulation (EIS). A recent trend attempts to represent vasculatures with three-dimensional (3D) surface meshes by multiview image and graphics-based techniques used in optical and laser scanners. Conversion from image volume data to 3D surface meshes, however, suffers from stairc...
Preprint
Full-text available
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring the long-range semantic contexts and geometric information on both RGB and depth features to infer salient objects. To achieve this, we formulate a d...
Preprint
Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also these detectors have difficulties learning latent information beneficial for detection in snow. To alleviate the two above problems, we first establish a real-world snow...
Article
As one of the prevalent topic mining methods, neural topic modeling has attracted a lot of interests due to the advantages of low training costs and strong generalisation abilities. However, the existing neural topic models may suffer from the feature sparsity problem when applied to short texts, due to the lack of context in each message. To allev...
Preprint
While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world ha...
Article
Full-text available
Digital games have become increasingly popular. However, many teachers may not have relevant knowledge and experience of designing and implementing digital game-based teaching in formal classrooms. This study proposed a collaborative design approach to facilitate pre-service teachers’ abilities of designing for learning with a digital game. To eval...
Preprint
Full-text available
Rain is one of the most common weather which can completely degrade the image quality and interfere with the performance of many computer vision tasks, especially under heavy rain conditions. We observe that: (i) rain is a mixture of rain streaks and rainy haze; (ii) the scene depth determines the intensity of rain streaks and the transformation in...
Article
Full-text available
The TPACK (technological pedagogical and content knowledge) framework is an influential theoretical foundation for teaching with technology research. This analysis of 1,608 empirical research studies of TPACK identifies trends and research topics from 2000 to 2020 using structural topic modelling and bibliometrics. The results showed that academic...
Article
Full-text available
Learning analytics (LA) has become an increasingly active field focusing on leveraging learning process data to understand and improve teaching and learning. With the explosive growth in the number of studies concerning LA, it is significant to investigate its research status and trends, particularly the thematic structure. Based on 3900 LA article...
Preprint
The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models trained on synthetic data to real-world rainy images. We raise an intriguing question -- if leveraging both a...
Preprint
Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate no...
Article
Full-text available
The recent development of deep learning-based natural language processing (NLP) methods has fostered many downstream applications in various fields. As one of the applications in the financial industry, fine-grained financial sentiment analysis (FSA) aims to understand the sentimental orientation, i.e., bullish or bearish, of financial texts by pre...
Article
Full-text available
Technology-enhanced collaborative writing (TECW) for second language development is receiving increasing research attention from educators and teachers. However, there have been few review studies investigating how teachers implement this activity, how they use technology for the implementation, and what challenges they have. To better prepare prac...
Preprint
Image filters are fast, lightweight and effective, which make these conventional wisdoms preferable as basic tools in vision tasks. In practical scenarios, users have to tweak parameters multiple times to obtain satisfied results. This inconvenience heavily discounts the efficiency and user experience. We propose basis composition learning on singl...
Chapter
This book brings together some thought-provoking papers around the theme of “Smart CALL.” The term “smart” nowadays means “connected to and exchanging information with other devices.” The contributions in this volume focus on a more human-centered perspective, namely the definition of smartness in terms of three qualities or dimensions: personaliza...
Article
Automated writing evaluation (AWE) plays an important role in writing pedagogy and has received considerable research attention recently; however, few reviews have been conducted to systematically analyze the recent publications arising from the many studies in this area. The present review aims to provide a comprehensive analysis of the literature...
Article
Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate no...
Article
Most of the existing object detection methods generate poor glass detection results, due to the fact that the transparent glass shares the same appearance with arbitrary objects behind it in an image. Different from traditional deep learning-based wisdoms that simply use the object boundary as an auxiliary supervision, we exploit label decoupling t...
Article
Three-dimensional (3D) imaging devices (e.g., depth cameras and optical and laser scanners) are frequently used to measure outdoor/indoor scenes. The measurement data represented by 3D point clouds is, however, usually noisy and should be denoised to facilitate subsequent applications. Existing point cloud denoising methods typically perform 1) poi...
Article
Full-text available
Research on sentic computing has received intensive attention in recent years, as indicated by the increased availability of academic literature. However, despite the growth in literature and researchers’ interests, there are no reviews on this topic. This study comprehensively explores the current research progress and tendencies, particularly the...
Article
Full-text available
Innovative information and communication technologies have reformed higher education from the traditional way to smart learning. Smart learning applies technological and social developments and facilitates effective personalized learning with innovative technologies, especially smart devices and online technologies. Smart learning has attracted inc...
Article
Gesture recognition by using Inertial Measurement Unit (IMU) sensors plays an important role in various Internet of Things (IOT) applications, e.g., smart home, intelligent medical system and so on. Traditional technologies usually utilize machine learning algorithms to train different gestures during the offline phase, then recognize the gesture d...
Article
Full-text available
Exploiting hand-crafted lexicon knowledge to enhance emotional or sentimental features at word-level has become a widely adopted method in emotion-relevant classification studies. However, few attempts have been made to explore the emotion construction in the classification task, which provides insights to how a sentence’s emotion is constructed. T...
Article
Full-text available
Topic models have been widely used for learning the latent explainable representation of documents, but most of the existing approaches discover topics in a flat structure. In this study, we propose an effective hierarchical neural topic model with strong interpretability. Unlike the previous neural topic models, we explicitly model the dependency...
Article
In recent years, the means of disease diagnosis and treatment have been improved remarkably, along with the continuous development of technology and science. Researchers have spent tremendous time and effort to build models, with an aim to assist medical practitioners in decision-making support. One of the greatest challenges remains is how to iden...
Article
The parallel Hierarchical Dirichlet Process (pHDP) is an efficient topic model which explores the equivalence of the generation process between Hierarchical Dirichlet Process (HDP) and Gamma-Gamma-Poisson Process (G2PP), in order to achieve parallelism at the topic level. Unfortunately, pHDP loses the non-parametric feature of HDP, i.e., the number...
Article
Soft computing, which focuses on approximate models and provides solutions to complicated real-life issues, has gained increasing momentum in application-specific domains like sentiment analysis and recommender systems to emulate cognitive processes behind decision-making. In this work, bibliometrics and structural topic modeling (STM) were adopted...
Article
Combining topological information and attributed information of nodes in networks effectively is a valuable task in network embedding. Nevertheless, many prior network embedding methods regarded attributed information of nodes as simple attribute sets or ignored them totally. In some scenarios, the hidden information contained in vertex attributes...
Article
Full-text available
Recent studies have increasingly investigated the effectiveness of both mobile and non-mobile digital game-based language learning. To gain an in-depth understanding of the differences in the effectiveness of mobile and non-mobile games, we compared studies from January 2000 to August 2020 investigating mobile game-based language learning (MGBLL) a...
Article
We propose a geometry-supporting dual convolutional neural network (GeoDualCNN) for both point cloud normal estimation and denoising. GeoDualCNN fuses the geometry domain knowledge that the underlying surface of a noisy point cloud is piecewisely smooth with the fact that a point normal is properly defined only when local surface smoothness is guar...
Article
Full-text available
In text categorization, Vector Space Model (VSM) has been widely used for representing documents, in which a document is represented by a vector of terms. Since different terms contribute to a document’s semantics in various degrees, a number of term weighting schemes have been proposed for VSM to improve text categorization performance. Much evide...
Article
In recent years, mobile applications (apps) have been increasingly used and investigated as a vocabulary learning approach. Despite the extensive use of commercial English as a Foreign Language (EFL) vocabulary learning apps in China, there is a lack of a review of these apps for a systematic Knowledge Management & E-Learning, 13(3), 250-272 251 un...
Article
This article examines the earliest examples of replication of bronze objects of complicated structure in China. It uses four quadrupeds from the Freer Gallery (National Museum of Asian Art, Smithsonian Institution), the Asian Art Museum of San Francisco, the British Museum, and the Yūrinkan Museum in Kyōto as examples to illustrate the complex tech...
Chapter
With the increasing demands of high-quality Chinese word embeddings for natural language processing, Chinese word embedding learning has attracted wide attention in recent years. Most of the existing research focused on capturing word semantics on large-scaled datasets. However, these methods are difficult to obtain effective word embeddings with l...
Chapter
This research investigated the perceptions of a group of students in a university in Hong Kong concerning peer assessment enhanced collaborative learning in a virtual learning environment. A total of 31 Chinese learners of English participated in the project and conducted online collaborative learning and peer assessment in Moodle, ZOOM, and Flipgr...
Chapter
Under the influence of COVID-19, online learning has become the primary way for students to continue their education. At all stages of online learning, active learning is a useful strategy promoting optimal understanding. However, there is a lack of relevant research on how to evaluate students’ active learning performance. This paper presents an o...
Conference Paper
Full-text available
We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequenc...
Article
Full-text available
Research has indicated strong relationships between learners’ affect and their learning. Emotions relate closely to students’ well-being, learning quality, productivity, and interaction. Digital game-based learning (DGBL) has been widely recognized to be effective in enhancing learning experiences and increasing student motivation. The field of emo...
Article
Full-text available
Automatic and accurate segmentation of breast lesion regions from ultrasonography is an essential step for ultrasound-guided diagnosis and treatment. However, developing a desirable segmentation method is very difficult due to strong imaging artifacts e.g., speckle noise, low contrast and intensity inhomogeneity, in breast ultrasound images. To sol...