Digital Commons Network^™

Parsing-Conditioned Anime Translation: A New Dataset And Method, Zhansheng Li, Yangyang Xu, Nanxuan Zhao, Yang Zhou, Yongtuo Liu, Dahua Lin, Shengfeng He

Research Collection School Of Computing and Information Systems

Anime is an abstract art form that is substantially different from the human portrait, leading to a challenging misaligned image translation problem that is beyond the capability of existing methods. This can be boiled down to a highly ambiguous unconstrained translation between two domains. To this end, we design a new anime translation framework by deriving the prior knowledge of a pre-Trained StyleGAN model. We introduce disentangled encoders to separately embed structure and appearance information into the same latent code, governed by four tailored losses. Moreover, we develop a FaceBank aggregation method that leverages the generated data of the StyleGAN, …

Nftdisk: Visual Detection Of Wash Trading In Nft Markets, Xiaolin Wen, Yong Wang, Xuanwu Yue, Feida Zhu, Min Zhu

Research Collection School Of Computing and Information Systems

With the growing popularity of Non-Fungible Tokens (NFT), a new type of digital assets, various fraudulent activities have appeared in NFT markets. Among them, wash trading has become one of the most common frauds in NFT markets, which attempts to mislead investors by creating fake trading volumes. Due to the sophisticated patterns of wash trading, only a subset of them can be detected by automatic algorithms, and manual inspection is usually required. We propose NFTDisk, a novel visualization for investors to identify wash trading activities in NFT markets, where two linked visualization modules are presented: a radial visualization module with …

Asdf: A Differential Testing Framework For Automatic Speech Recognition Systems, Daniel Hao Xian Yuen, Andrew Yong Chen Pang, Zhou Yang, Chun Yong Chong, Mei Kuan Lim, David Lo

Research Collection School Of Computing and Information Systems

Recent years have witnessed wider adoption of Automated Speech Recognition (ASR) techniques in various domains. Consequently, evaluating and enhancing the quality of ASR systems is of great importance. This paper proposes Asdf, an Automated Speech Recognition Differential Testing Framework to test ASR systems. Asdf extends an existing ASR testing tool, the CrossASR++, which synthesizes test cases from a text corpus. However, CrossASR++ fails to make use of the text corpus efficiently and provides limited information on how the failed test cases can improve ASR systems. To address these limitations, our tool incorporates two novel features: (1) a text transformation module …

Open-Set Domain Adaptation By Deconfounding Domain Gaps, Xin Zhao, Shengsheng Wang, Qianru Sun

Research Collection School Of Computing and Information Systems

Open-Set Domain Adaptation (OSDA) aims to adapt the model trained on a source domain to the recognition tasks in a target domain while shielding any distractions caused by open-set classes, i.e., the classes “unknown” to the source model. Compared to standard DA, the key of OSDA lies in the separation between known and unknown classes. Existing OSDA methods often fail the separation because of overlooking the confounders (i.e., the domain gaps), which means their recognition of “unknown classes” is not because of class semantics but domain difference (e.g., styles and contexts). We address this issue by explicitly deconfounding domain gaps …

Morphologically-Aware Vocabulary Reduction Of Word Embeddings, Chong Cher Chia, Maksim Tkachenko, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

We propose SubText, a compression mechanism via vocabulary reduction. The crux is to judiciously select a subset of word embeddings which support the reconstruction of the remaining word embeddings based on their form alone. The proposed algorithm considers the preservation of the original embeddings, as well as a word’s relationship to other words that are morphologically or semantically similar. Comprehensive evaluation of the compressed vocabulary reveals SubText’s efficacy on diverse tasks over traditional vocabulary reduction techniques, as validated on English, as well as a collection of inflected languages.

Does Deep Learning Improve The Performance Of Duplicate Bug Report Detection? An Empirical Study, Yuan Jiang, Xiaohong Su, Christoph Treude, Chao Shang, Tiantian Wang

Research Collection School Of Computing and Information Systems

Do Deep Learning (DL) techniques actually help to improve the performance of duplicate bug report detection? Prior studies suggest that they do, if the duplicate bug report detection task is treated as a binary classification problem. However, in realistic scenarios, the task is often viewed as a ranking problem, which predicts potential duplicate bug reports by ranking based on similarities with existing historical bug reports. There is little empirical evidence to support that DL can be effectively applied to detect duplicate bug reports in the ranking scenario. Therefore, in this paper, we investigate whether well-known DL-based methods outperform classic information …

A Learner-Verifier Framework For Neural Network Controllers And Certificates Of Stochastic Systems, Krishnendu Chatterjee, Thomas A. Henzinger, Dorde Zikelic, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Reinforcement learning has received much attention for learning controllers of deterministic systems. We consider a learner-verifer framework for stochastic control systems and survey recent methods that formally guarantee a conjunction of reachability and safety properties. Given a property and a lower bound on the probability of the property being satisfied, our framework jointly learns a control policy and a formal certificate to ensure the satisfaction of the property with a desired probability threshold. Both the control policy and the formal certificate are continuous functions from states to reals, which are learned as parameterized neural networks. While in the deterministic case, …

Interconnectedness And Financial Stability In The Era Of Artificial Intelligence, Nydia Remolina Leon

Research Collection Yong Pung How School Of Law

This chapter explains AI use cases may amplify some threats to the stability of the financial system. It argues that lack of a consistent approach to AI Governance by financial regulators and limited oversight on some AI models in terms of systemic risks need to be addressed to preserve the stability of the financial system. To illustrate the problem and propose specific policy recommendations, the chapter first explains how the widespread use AI in finance impacts systemic risk in the financial sector. Then, it explains why trustworthiness of AI encompasses not only the typical ethical principles about transparency, explainability, fairness, …

Academic Libraries In An Open Access And Ai First World – An Attempt To Peer Into The Future, Aaron Tay

Research Collection Library

Technology is rapidly advancing, and AI is becoming more sophisticated everyday, But what is even more exciting is that academic libraries are going to be impacted even more. Why is that? It's because even the most advanced algorithm will not work without data to train on.

Hedging Cryptos With Bitcoin Futures, Francis Liu, Natalie Packham, Meng-Jou Lu, Wolfgang Karl Haerdle

Sim Kee Boon Institute for Financial Economics

The introduction of derivatives on Bitcoin enables investors to hedge risk exposures in cryptocurrencies. Because of volatility swings and jumps in cryptocurrency prices, the traditional variance-based approach to obtain hedge ratios may not be suitable for hedgers. In this work, we consider two extensions of the traditional approach: first, different dependence structures are modelled by different copulae, such as the Gaussian, Student-t, Normal Inverse Gaussian and Archimedean copulae; second, different risk measures, such as value-at-risk, expected shortfall and spectral risk measures are employed to find the optimal hedge ratio. Extensive out-of-sample tests using the data from the time …

Highway To The Comfort Zone: History Of The Psychrometric Chart, Eric Teitelbaum, Clayton Miller, Forrest Meggers

Research Collection College of Integrative Studies

The psychrometric chart is the most common data visualization technique for the designers of thermal comfort systems worldwide. From its humble roots as means of expressing the characteristics of air in building systems design, the use of the chart has grown to include the representation of the zones of human thermal comfort according to both conventional and adaptive models. In this paper, we present an extensive history of this development and the fallacies with representing comfort simply as a box that sometimes moves on the chart. The origins of the link between refrigeration control and comfort control are examined through …

Topic Recommendation For Github Repositories: How Far Can Extreme Multi-Label Learning Go?, Ratnadira Widyasari, Zhipeng Zhao, Thanh Le Cong, Hong Jin Kang, David Lo

Research Collection School Of Computing and Information Systems

GitHub is one of the most popular platforms forversion control and collaboration. In GitHub, developers are ableto assign related topics to their repositories, which is helpfulfor finding similar repositories. The topics that are assigned torepositories are varied and provide salient descriptions of therepository; some topics describe the technology employed in aproject, while others describe functionality of the project, itsgoals, and its features. Topics are part of the metadata of arepository and are useful for the organization and discoverabilityof the repository. However, the number of topics is large andthis makes it challenging to assign a relevant set of topics to arepository. …

Detecting C++ Compiler Front-End Bugs Via Grammar Mutation And Differential Testing, Haoxin Tu, He Jiang, Zhide Zhou, Yixuan Tang, Zhilei Ren, Lei Qiao, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

C++ is a widely used programming language and the C++ front-end is a critical part of a C++ compiler. Although many techniques have been proposed to test compilers, few studies are devoted to detecting bugs in C++ compiler. In this study, we take the first step to detect bugs in C++ compiler front-ends. To do so, two main challenges need to be addressed, namely, the acquisition of test programs that are more likely to trigger bugs in compiler front-ends and the bug identification from complicated compiler outputs. In this article, we propose a novel framework named Ccoft to detect bugs …

Harnessing The Power Of Video Ads, Linyi Li

Asian Management Insights

In digital advertising, video ads as a top-of-funnel function have a longer-lasting efect than display and search ads on a consumer's consciousness.

Improving Rumor Detection By Promoting Information Campaigns With Transformer-Based Generative Adversarial Learning, Jing Ma, Jun Li, Wei Gao, Yang Yang, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Rumors can cause devastating consequences to individuals and our society. Analysis shows that the widespread of rumors typically results from deliberate promotion of information aiming to shape the collective public opinions on the concerned event. In this paper, we combat such chaotic phenomenon with a countermeasure by mirroring against how such chaos is created to make rumor detection more robust and effective. Our idea is inspired by adversarial learning method originated from Generative Adversarial Networks (GAN). We propose a GAN-style approach, where a generator is designed to produce uncertain or conflicting voices, further polarizing the original conversational threads to boost …

Report On The Challenges Which Digital Assets Pose For Tax Systems With A Special Focus On Developing Countries, Vincent Ooi

Research Collection Yong Pung How School Of Law

The paper highlights the need for governments to carefully consider the implications which the rise of crypto assets can have on tax systems, noting that the absence of a deliberate policy position would be a policy decision in itself, with consequences for the tax base. It discusses four main classes of tax risks which crypto assets pose.Firstly, crypto assets and crypto transactions can act as ‘functional substitutes’ for traditional assets and transactions. As existing tax laws are drafted without crypto assets in mind, this can produce a host of unintended tax consequences and produce opportunities for tax arbitrage.Secondly, the values …

Family Wealth Advisory Services In China – What Kind Of Advisors Can Be More Competent And Successful?, Yang Shen

Dissertations and Theses Collection (Open Access)

High net worth wealth owners generally need various advisory services to meet their wealth management needs, such as investment / global asset allocation, intergenerational succession planning, personal and family tax planning, next-generation education, health management, immigration arrangement for family members, etc.

At the current stage, this paper tries to answer below central research questions for Chinese wealth advisors:

1. From the Perspective of high-net-worth individuals (HNWI) in China, what characteristics should their wealth advisors bear to be considered competent?
2. Which key competency factors are mostly important in making the wealth advisor successful (reflected through performance rating of wealth advisors)?

The research …

How Do Values Matter In The Relation Between Organizational Trust And Performance? The Case Of China, Lu Jiang

Dissertations and Theses Collection (Open Access)

Trust in organizations has been demonstrated and discussed widely in research in Western cultures. With China’s rapidly developing economy, more and more Western managers work in China now, while an increasing number of Chinese managers work overseas. This makes research on the way trust in organizations operates in Chinese culture an important topic. This study contributes to the literature from the perspective of the way values matter in the relation between organizational trust and performance in China. This research proposes that in the context of China, employees’ and supervisor’s Confucian value system affects the trust in the supervisor positively, which …

Humanized Management, Fairness Perception And Health Of Merchant Ecosystem: Driving Mechanisms Of The Digital Age, Zeyong Zhuang

Dissertations and Theses Collection (Open Access)

In the era of digital transformation, the competition among individual enterprises has evolved into competition of business ecosystems, and the merchants in shopping malls have evolved from atomistic competition to ecological competition. Therefore, merchants must ensure the health of business ecosystems to establish competitive advantages. This study uses the survey data of merchants in five shopping malls in Guangzhou to empirically test the mechanism of the effect of humanized management on the health of business ecosystems in the context of digital transformation.

The empirical results show that: 1. Humanized management of shopping malls helps to build trust and loyalty, promote …

Dminer: Dashboard Design Mining And Recommendation, Yanna Lin, Haotian Li, Aoyu Wu, Yong Wang, Huamin Qu

Research Collection School Of Computing and Information Systems

Dashboards, which comprise multiple views on a single display, help analyze and communicate multiple perspectives of data simultaneously. However, creating effective and elegant dashboards is challenging since it requires careful and logical arrangement and coordination of multiple visualizations. To solve the problem, we propose a data-driven approach for mining design rules from dashboards and automating dashboard organization. Specifically, we focus on two prominent aspects of the organization: arrangement , which describes the position, size, and layout of each view in the display space; and coordination , which indicates the interaction between pairwise views. We build a new dataset containing 854 …

Blockscope: Detecting And Investigating Propagated Vulnerabilities In Forked Blockchain Projects, Xiao Yi, Yuzhou Fang, Daoyuan Wu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Due to the open-source nature of the blockchain ecosystem, it is common for new blockchains to fork or partially reuse the code of classic blockchains. For example, the popular Dogecoin, Litecoin, Binance BSC, and Polygon are all variants of Bitcoin/Ethereum. These “forked” blockchains thus could encounter similar vulnerabilities that are propagated from Bitcoin/Ethereum during forking or subsequently commit fetching. In this paper, we conduct a systematic study of detecting and investigating the propagated vulnerabilities in forked blockchain projects. To facilitate this study, we propose BlockScope, a novel tool that can effectively and efficiently detect multiple types of cloned vulnerabilities given …

Volere: Leakage Resilient User Authentication Based On Personal Voice Challenges, Rui Zhang, Zheng Yan, Xuerui Wang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Voiceprint Authentication as a Service (VAaS) offers great convenience due to ubiquity, generality, and usability. Despite its attractiveness, it suffers from user voiceprint leakage over the air or at the cloud, which intrudes user voice privacy and retards its wide adoption. The literature still lacks an effective solution on this issue. Traditional methods based on cryptography are too complex to be practically deployed while other approaches distort user voiceprints, which hinders accurate user identification. In this article, we propose a leakage resilient user authentication cloud service with privacy preservation based on random personal voice challenges, named VOLERE (VOice LEakage REsilient). …

Investigating Noticeable Hand Redirection In Virtual Reality Using Physiological And Interaction Data, Martin Feick, Kora Regitz, Anthony Tang, Jungbluth

Research Collection School Of Computing and Information Systems

Hand redirection is effective so long as the introduced offsets are not noticeably disruptive to users. In this work we investigate the use of physiological and interaction data to detect movement discrepancies between a user's real and virtual hand, pushing towards a novel approach to identify discrepancies which are too large and therefore can be noticed. We ran a study with 22 participants, collecting EEG, ECG, EDA, RSP, and interaction data. Our results suggest that EEG and interaction data can be reliably used to detect visuo-motor discrepancies, whereas ECG and RSP seem to suffer from inconsistencies. Our findings also show …

Take Notes, Not Photos: Mind-Wandering Mediates The Impact Of Note-Taking Strategies On Video-Recorded Lecture Learning Performance, Sarah Shi Hui Wong, Stephen Wee Hun Lim

Research Collection School of Social Sciences

In two experiments (N = 200), we compared the effects of longhand note-taking, photographing lecture materials with a smartphone camera, and not taking any notes on video-recorded lecture learning. Experiment 1 revealed a longhand-superiority effect: Longhand note-takers outperformed photo-takers and control learners on a recall test, notwithstanding an equal opportunity to review their learning material right before being tested, and even when photo-takers and control participants reviewed an exact transcript of the lecture slides via their photos or printouts, whereas longhand note-takers accessed only a fraction of the content as captured in their handwritten notes. Photo-takers performed comparably to learners …

Relative Power And Interpersonal Trust, Christilene Du Plessis, My Hoang Bao Nguyen, Trevor A. Foulk, Michael Schaerer

Research Collection Lee Kong Chian School Of Business

Because trust is essential in the development and maintenance of well-functioning relationships, scholars across numerous scientific disciplines have sought to determine what causes people to trust others. Power dynamics are known to predict trust, but research on the relationship between power and trust is inconclusive, with mixed results and without systematic consideration of how the relative power distribution within dyadic relationships may influence trust in those relationships. Building on interdependence theory, we propose that both individuals in an unequal-power dyad trust each other less than individuals in an equal-power dyad because unequal-power dyads heighten the perception of a conflict of …

Impacts Of Distributive Comparison Behavior On Corporate Social Responsibility In Supply Chains: The Role Of Small Firms, Mingzheng Wang, Xin Fang, Zizhuo Wang, Ying-Ju Chen

Research Collection Lee Kong Chian School Of Business

Problem definition: In this paper, we explore how a firm’s concern about profit distribution and the size of downstream firms in supply chains affect corporate social responsibility (CSR) investment strategy. Methodology/results: In a supply chain consisting of one supplier and one manufacturer, both players decide whether to invest to reduce CSR violations, and they negotiate over a wholesale price. Distributive comparison behavior makes the manufacturer compare the profit with his equitable payoff, which is determined by the supplier’s profit. Advantageous (resp. disadvantageous) inequality occurs when the manufacturer’s profit is higher (resp. lower) than the manufacturer’s equitable payoff. We compare this …

Investigating Guardian Awareness Techniques To Promote Safety In Virtual Reality, Sixuan Wu, Jiannan Li, Maurício Sousa, Tovi Grossman

Research Collection School Of Computing and Information Systems

Virtual Reality (VR) can completely immerse users in a virtual world and provide little awareness of bystanders in the surrounding physical environment. Current technologies use predefined guardian area visualizations to set safety boundaries for VR interactions. However, bystanders cannot perceive these boundaries and may collide with VR users if they accidentally enter guardian areas. In this paper, we investigate four awareness techniques on mobile phones and smartwatches to help bystanders avoid invading guardian areas. These techniques include augmented reality boundary overlays and visual, auditory, and haptic alerts indicating bystanders' distance from guardians. Our findings suggest that the proposed techniques effectively …

Exogenous Loss Of Analyst Coverage And Choice Of Audit Quality, Simon Yu Kit Fung, Zheng Wang, Liandong Zhang, Xindong Zhu

Research Collection School Of Accountancy

We show that a firm’s likelihood of appointing auditors with industry expertise or with a larger office increases after the firm is affected by an exogenous reduction in analyst coverage, relative to its matched control firms. This effect is stronger for affected firms with greater reductions in analyst monitoring, for smaller or younger firms, for firms with lower institutional or CEO ownership, and when the lost analysts are more effective monitors. We further show that affected firms that switch to high-quality auditors receive more positive market reaction, experience a smaller decrease in stock liquidity and a smaller increase in cost …

Continuity, History, And Identity: Why Bongbong Marcos Won The 2022 Philippine Presidential Election, Dean C. Dulay, Allen Hicken, Anil Menon, Ronald Holmes

Research Collection School of Social Sciences

In May of 2022, Bongbong Marcos won a commanding 59 percent of the vote to become president of the Philippines. His victory was, on some level, shocking to scholars and analysts of Philippine politics. As a result, a plethora of different theories have been proposed, in an attempt to explain why Marcos won. In this paper, we use nationally representative survey data to explore which factors predict (and do not predict) voting intention for Marcos. We find that, a) support for former President Rodrigo Duterte, b) positive perceptions of the late President Ferdinand Marcos and martial law, and c) ethnic …

'Kevin Vallier' Trust In A Polarized Age, Chandran Kukathas

Research Collection School of Social Sciences

Vallier offers a defence of liberalism that is publicly justified as an answer to political polarization. This critique argues that the philosophical solution he offers - a version of liberalism more likely to be endorsed by moderately idealized agents - may not succeed because the source of polarization lies elsewhere: in resentments arising out of changed social conditions and the alienation of parts of society unhappy with the very liberal narrative in question.