Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 2611 - 2640 of 23256

Full-Text Articles in Entire DC Network

Community Discovery Over Attributed Graphs, Yudong Niu Jun 2024

Community Discovery Over Attributed Graphs, Yudong Niu

Dissertations and Theses Collection (Open Access)

Community discovery, as a fundamental problem in graph mining, finds applications in various domains such as biological analysis, system optimization and fraud detection. Although many efforts have been made to address community discovery based on graph topology, few works have been devoted to community discovery over attributed graphs, where graphs are equipped with attribute information such as node and edge types. Thus, this thesis is devoted to designing innovative solutions that can utilize the attribute information together with graph topology for community discovery. In particular, we study novel problems with efficient algorithms for both homogeneous and heterogeneous attributed graphs and …

Go to article

An Investigation On The Effects Of Fund Manager’S Narcissism On Fund Performance, Ning Zhou Jun 2024

An Investigation On The Effects Of Fund Manager’S Narcissism On Fund Performance, Ning Zhou

Dissertations and Theses Collection (Open Access)

As the capital market continues to expand, the benefits of securities investment funds have become increasingly prominent. However, for investors, selecting the right investment fund from numerous options can be more challenging than directly choosing stocks. The process of seeking investment opportunities also involves selecting the right fund manager, a step often underestimated by investors. Research in behavioral finance indicates that fund managers tend to exhibit irrational decision behavior under immense pressure and uncertain investment outcomes. Narcissism as a psychological trait may influence fund managers’ decision-making behavior. This study, through questionnaires and empirical analysis, examines the narcissistic traits of Chinese …

Go to article

City Shape, Commuting Time And Workplace Choice: Analyzing Urban Spatial Form In China, Shen Fu Jun 2024

City Shape, Commuting Time And Workplace Choice: Analyzing Urban Spatial Form In China, Shen Fu

Dissertations and Theses Collection (Open Access)

This paper investigates the relationship between city shape, commuting time, and workplace choice within the context of Chinese cities. Using an urban form measure, nCohesion, and nighttime light data, I constructed the China City Shape Database for 263 Chinese cities. The empirical analysis reveals a counterintuitive finding: cities with less compact shapes, despite having longer within-city distances, are associated with shorter commuting times. This is because residents in poorly shaped cities tend to select workplaces closer to their homes to mitigate commuting difficulties. The findings suggest that improving city shape alone may not reduce commuting times; instead, enhancing transportation infrastructure …

Go to article

Childlessness, Social Network Profiles In Midlife And Late Adulthood, And Their Implications For Subjective Well-Being, Bussarawan Teerawichitchainan, Dahye Kim, Christine Ho Jun 2024

Childlessness, Social Network Profiles In Midlife And Late Adulthood, And Their Implications For Subjective Well-Being, Bussarawan Teerawichitchainan, Dahye Kim, Christine Ho

Research Collection School Of Economics

Objectives: Despite the rising prevalence of individuals reaching advanced age without children, little is known about the diversity of support networks within childless populations. We examine the network profiles of childless adults aged 50+ in Singapore, which observes high childlessness rates despite societal emphasis on familism. Methods: We employ latent class analysis to derive network typology based on a 2022 nationwide survey in Singapore. Additionally, we use logistic regression analyses to investigate the sociodemographic correlates of childless individuals' network types and the associations between these network types and subjective well-being. Results: Childless Singaporeans form a heterogeneous group characterized by different …

Go to article

Enhancing Student Engagement In Introductory Economics With Interactive Videos And Synthesized Readings In Flipped Learning, Bei Hong, Duan Ning, Magdeleine Lew Jun 2024

Enhancing Student Engagement In Introductory Economics With Interactive Videos And Synthesized Readings In Flipped Learning, Bei Hong, Duan Ning, Magdeleine Lew

Research Collection School Of Economics

A major challenge faced by university economics instructors is to find more time to incorporate active learning into the classroom, which encourages student participation. As a result, more instructors choose to flip their classrooms, in which students are encouraged to perform preparatory reading or watch videos to participate more meaningfully and learn more effectively. This study aims to examine how pre-lecture materials enhance student participation by examining the effectiveness of two types of materials: interactive videos and synthesized readings. The synthesized readings contain essential information extracted from the textbook and is presented in a structured manner with highlighted key points. …

Go to article

Criticality Aware Canvas-Based Visual Perception At The Edge, Ila Gokarn Jun 2024

Criticality Aware Canvas-Based Visual Perception At The Edge, Ila Gokarn

Research Collection School Of Computing and Information Systems

Efficient and effective machine perception remains a formidable challenge in sustaining high fidelity and high throughput of perception tasks on affordable edge devices. This is especially due to the continuing increase in resolution of sensor streams (e.g., video input streams generated by 4K/8K cameras and neuromorphic event cameras that produce ≥ 10 MEvents/second) and computational complexity of Deep Neural Network (DNN) models, which overwhelms edge platforms, adversely impacting machine perception efficiency. Given the insufficiency of the available computation resources, a question then arises on whether selected regions/components of the perception task can be prioritized (and executed preferentially) to achieve highest …

Go to article

Fitting The Communication Forum To The Mediation Fuss: Choosing The Appropriate Communication Mode For Mediation In The Post-Pandemic World, Dorcas Quek Anderson Jun 2024

Fitting The Communication Forum To The Mediation Fuss: Choosing The Appropriate Communication Mode For Mediation In The Post-Pandemic World, Dorcas Quek Anderson

Research Collection Yong Pung How School Of Law

Since the COVID-19 pandemic, mediations have shifted dramatically from face-to-face settings to the virtual realm, resulting in the widespread acceptance of using virtual communication channels, including videoconferencing, audio calls, and text messaging. With the waning of the pandemic, mediators and parties presently face a plethora of choices in fitting their mediation to the appropriate communication channel. Thus, having an accurate, evidence-based understanding of different communication modes’ impact on mediation is necessary to design an optimal mediation process.Some decades ago, Sander and Goldberg formulated the phrase “fitting the forum to the fuss” to describe the process of choosing the most appropriate …

Go to article

Ai Employment Decision-Making: Integrating The Equal Opportunity Merit Principle And Explainable Ai, Gary Kok Yew Chan Jun 2024

Ai Employment Decision-Making: Integrating The Equal Opportunity Merit Principle And Explainable Ai, Gary Kok Yew Chan

Research Collection Yong Pung How School Of Law

Artificial intelligence (AI) tools used in employment decision-making cut across the multiple stages of job advertisements, shortlisting, interviews and hiring, and actual and potential bias can arise in each of these stages. One major challenge is to mitigate AI bias and promote fairness in opaque AI systems. This paper argues that the equal opportunity merit principle is an ethical approach for fair AI employment decision-making. Further, explainable AI can mitigate the opacity problem by placing greater emphasis on enhancing the understanding of reasonable users (employing organisations) and affected persons (employees and job candidates) as to the AI output. Both the …

Go to article

Shaping Green Regionalism: New Trade Law Approaches To Environmental Sustainability, Pasha L. Hsieh Jun 2024

Shaping Green Regionalism: New Trade Law Approaches To Environmental Sustainability, Pasha L. Hsieh

Research Collection Yong Pung How School Of Law

Green regionalism aims to mutually reinforce environmental governance and economic integration. The article provides the first analysis of green regionalism in international law. It argues that green regionalism represents a paradigm shift in global normative endeavours towards environmental sustainability. By contextualising three waves of global regionalism, the article unveils the evolving architecture of green regionalism alongside negotiations of the World Trade Organization and multilateral environmental agreements. Moreover, it sheds light on the pertinent disputes and features of new green initiatives galvanised by the European Union, the United States and Asia-Pacific countries. These developments are pivotal in understanding the trade-environment nexus …

Go to article

Re-Calibration Of Curial Intervention In Public Policy Challenges Against Arbitral Awards, Darius Chan, Elias Ngai Hum Khong Jun 2024

Re-Calibration Of Curial Intervention In Public Policy Challenges Against Arbitral Awards, Darius Chan, Elias Ngai Hum Khong

Research Collection Yong Pung How School Of Law

When an award debtor challenges an award on public policy grounds, usually the principle of finality prevails, and courts will consider the award debtor bound by the decision of the tribunal. However, because public policy has implications beyond the disputing parties themselves, some courts consider themselves justified in reviewing the award. There is therefore a tension between finality versus the court’s duty to stand as the guardian of public policy. Whether a review of an award should be allowed under this ground, and if so, the extent of permissible review, differs across various jurisdictions. For instance, common law authorities have …

Go to article

Sustainability And The Sunlight Of Disclosure: Esg Disclosure In Three Asian Financial Centres, Rachel Phang, Yaru Chia Jun 2024

Sustainability And The Sunlight Of Disclosure: Esg Disclosure In Three Asian Financial Centres, Rachel Phang, Yaru Chia

Research Collection Yong Pung How School Of Law

The prevailing paradigm of sustainable finance places great importance on environmental, social and governance (ESG) information and, therefore, on the mechanism of reporting and disclosure. This article presents, analyses and compares the approaches to ESG disclosure in three Asian financial centres: Singapore, Hong Kong and Shanghai. The article uncovers commonalities and divergences in the drivers, dynamics, content and trends of ESG disclosure in the selected jurisdictions. In doing so, it looks forwards, seeking to anticipate and shape the development of ESG disclosure in Asia. At the same time, it looks beyond ESG disclosure, remaining mindful that the mechanism itself is …

Go to article

Law, Love, And Freedom: From The Sacred To The Secular, Seow Hon Tan Jun 2024

Law, Love, And Freedom: From The Sacred To The Secular, Seow Hon Tan

Research Collection Yong Pung How School Of Law

In this book, published under a series on the intersection of law and Christianity, Neoh undertakes the ambitious project of exploring the concepts of law, love, and freedom to illuminate the moral vision which underlies our secular legal order.

Go to article

Fintech: Finance, Technology And Regulation, Nydia Remolina Jun 2024

Fintech: Finance, Technology And Regulation, Nydia Remolina

Research Collection Yong Pung How School Of Law

Fintech: finance, technology and regulation, by Ross P. Buckley, Douglas W. Arner,and Dirk A. Zetzsche, Cambridge, Cambridge University Press, 2024, 330 pp, £29.99(paperback), ISBN 978-1-009-07821-4

Go to article

The Irreducible Otherness Of Desi And Desire In Singapore’S Gurdwaras: Moral Boundary-Making In The Shadows Of A Multicultural Society, Orlando Woods, Lily Kong Jun 2024

The Irreducible Otherness Of Desi And Desire In Singapore’S Gurdwaras: Moral Boundary-Making In The Shadows Of A Multicultural Society, Orlando Woods, Lily Kong

Research Collection College of Integrative Studies

This article considers the emergence of new multiculturalisms taking root in Asia by exploring how value-based frameworks and moral judgements are deployed to create new lines of difference within co-ethnic communities. These frameworks and judgements cause multiculturalism to become a more subjective, and thus splintered construct that is increasingly decoupled from state discourse. Further, it considers how religious spaces are typically associated with the performance of morally “right” attitudes and behaviours, and therefore provide fertile yet underexplored sites through which multicultural subjectivities are formed and enacted. It illustrates these theoretical ideas through an empirical examination of how moral boundary-making within …

Go to article

Assessing Impact Of Urban Densification On Outdoor Microclimate And Thermal Comfort Using Envi-Met Simulations For Combined Spatial-Climatic Design (Cscd) Approach, Shreya Banerjee, Rachel X.Y. Pek, Sin Kang Yik, Graces N. Ching, Xiang Tian Ho, Dzyuban Yuliya, Peter J. Crank, Juan A. Acero, Winston T. L. Chow Jun 2024

Assessing Impact Of Urban Densification On Outdoor Microclimate And Thermal Comfort Using Envi-Met Simulations For Combined Spatial-Climatic Design (Cscd) Approach, Shreya Banerjee, Rachel X.Y. Pek, Sin Kang Yik, Graces N. Ching, Xiang Tian Ho, Dzyuban Yuliya, Peter J. Crank, Juan A. Acero, Winston T. L. Chow

Research Collection College of Integrative Studies

Future urban planning requires context-specific integration of spatial design and microclimate especially for tropical cities with extreme weather conditions. Thus, we propose a Combined Spatial-Climatic Design approach to assess impact of urban densification on annual outdoor thermal comfort performance employing ENVI-met simulations for Singapore. We first consider building bylaws and residential site guidelines to develop eight urban-density site options for a target population range. We further classify annual weather data into seven weather-types and use them as boundary conditions for the simulations. Comparing such fifty-six combined spatial-climatic simulation outputs by analyzing Outdoor Thermal Comfort Autonomy, we report the influence of …

Go to article

Digital Transformation: Two Sides Of A Coin, Tze K Koh Jun 2024

Digital Transformation: Two Sides Of A Coin, Tze K Koh

Research Collection College of Integrative Studies

It is of paramount importance to examine the intersection of digital transformation and sustainability. At the same time, there is a growing imbalance between digitalisation within the workforce and the pace at which sustainability awareness is picking up. Addressing this gap is crucial.

Go to article

Platform Infrastructures: Mobilizing Passengers, Immobilizing Civic Imaginations?, Andrew Stokols Jun 2024

Platform Infrastructures: Mobilizing Passengers, Immobilizing Civic Imaginations?, Andrew Stokols

Research Collection College of Integrative Studies

Anyone who has ever used a ride-hailing app in the middle of rush hour “surge pricing” has experienced a painful reality—platform companies once described as “disrupters” now control a critical urban infrastructure and with it the power to extract profits, shape urban mobility markets, and collect millions of data points on drivers, consumers, and urban mobility patterns. The idea of the “platform economy” is now firmly ensconced in scholarly and public discourse. Platform firms, according to Nick Srnicek, are “digital infrastructures that enable two or more groups to interact . . . and position themselves as intermediaries that bring together …

Go to article

A Data-Driven Agent-Based Model Of Occupants’ Thermal Comfort Behaviors For The Planning Of District-Scale Flexible Work Arrangements, Martín Mosteiro-Romero, Matias Quintana, Rudi Stouffs, Clayton Miller Jun 2024

A Data-Driven Agent-Based Model Of Occupants’ Thermal Comfort Behaviors For The Planning Of District-Scale Flexible Work Arrangements, Martín Mosteiro-Romero, Matias Quintana, Rudi Stouffs, Clayton Miller

Research Collection College of Integrative Studies

In a global context of increasing flexibility in the way workplaces and the districts in which they are located are used, there is a need for occupant-driven approaches to plan urban energy systems. Several authors have suggested the use of agent-based models (ABM) of building occupants in urban building energy simulations due to their ability to reproduce emergent behaviors from individual agents’ actions. However, few works in the literature take full advantage of the ABM paradigm, accounting for both occupant presence and energy-relevant behaviors at the district scale. In this work, we propose a methodology to develop a data-driven, agent-based …

Go to article

Creating Synthetic Energy Meter Data Using Conditional Diffusion And Building Metadata, Chun Fu, Hussain Kazmi, Matias Quintana, Clayton Miller Jun 2024

Creating Synthetic Energy Meter Data Using Conditional Diffusion And Building Metadata, Chun Fu, Hussain Kazmi, Matias Quintana, Clayton Miller

Research Collection College of Integrative Studies

Advances in machine learning and increased computational power have driven progress in energy-related research. However, limited access to private energy data from buildings hinders traditional regression models relying on historical data. While generative models offer a solution, previous studies have primarily focused on short-term generation periods (e.g., daily profiles) and a limited number of meters. Thus, the study proposes a conditional diffusion model for generating high-quality synthetic energy data using relevant metadata. Using a dataset comprising 1,828 power meters from various buildings and countries, this model is compared with traditional methods like Conditional Generative Adversarial Networks (CGAN) and Conditional Variational …

Go to article

Factors Affecting Online Consumers' Cultural Presence And Cultural Immersion Experiences In Live Streaming Shopping, Lifu Li, Kyeong Kang, Yafei Feng, Anqi Zhao Jun 2024

Factors Affecting Online Consumers' Cultural Presence And Cultural Immersion Experiences In Live Streaming Shopping, Lifu Li, Kyeong Kang, Yafei Feng, Anqi Zhao

Research Collection School Of Computing and Information Systems

This paper conducts research on the interaction between ethnic minority group (EMG) live streamers and online consumers, aiming to present how EMG live streamers’ appearance and interaction factors affect online consumers’ cultural experience during live streaming shopping. Based on the social presence theory and the immersion theory, this paper explores how EMG live streamers impact online consumers’ cultural experience, and it designs personal EMG knowledge as a moderating variable under specific social and cultural backgrounds. Through analysing 325 online questionnaires based on the partial least squares path modelling and variance-based structural equation modelling (PLS-SEM), the study results support that both …

Go to article

On Efficient Object-Detection Nas For Adas On Edge Devices, Diksha Gupta, Rhui Dih Lee, Laura Wynter Jun 2024

On Efficient Object-Detection Nas For Adas On Edge Devices, Diksha Gupta, Rhui Dih Lee, Laura Wynter

Research Collection School Of Computing and Information Systems

Object detection is a crucial building block for Advanced Driving Assistance Systems (ADAS). These systems require real-time accurate detection on resource-constrained edge devices. Deep learning models are emerging as popular techniques over traditional methods with superior performance. A hurdle in deploying these models is the inference time and computational cost of these models, in addition to training challenges for specialized tasks.We address this using supernet training-based neural architecture search (NAS) to obtain a variety of object detection models at a scale specific to the ADAS application. To this end, we consider a convolutional neural network-based object detection model. We produce …

Go to article

Improving Interpretable Embeddings For Ad-Hoc Video Search With Generative Captions And Multi-Word Concept Bank, Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan Jun 2024

Improving Interpretable Embeddings For Ad-Hoc Video Search With Generative Captions And Multi-Word Concept Bank, Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan

Research Collection School Of Computing and Information Systems

Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small sizes of available video-text datasets and the low quality of concept banks, which results in the failures of unseen queries and the out-of-vocabulary problem. This paper addresses these two problems by constructing a new dataset and developing a multi-word concept bank. Specifically, capitalizing on a generative model, we construct a new dataset consisting of 7 million generated text and video pairs for pre-training. To …

Go to article

Imitating Cost-Constrained Behaviors In Reinforcement Learning, Qian Shao, Pradeep Varakantham, Shih-Fen Cheng Jun 2024

Imitating Cost-Constrained Behaviors In Reinforcement Learning, Qian Shao, Pradeep Varakantham, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative to solving these problems. Generally speaking, imitation learning is designed to learn either the reward (or preference) model or directly the behavioral policy by observing the behavior of an expert. Existing work in imitation learning and inverse reinforcement learning has focused on imitation primarily in unconstrained settings (e.g., no limit on fuel consumed by the vehicle). However, in many real-world domains, the behavior of an expert …

Go to article

The Next 'Deep' Thing In X To Z Marketing: An Artificial Intelligence Driven Approach, Vincent Charles, Nripendra Rana, Ilias O. Pappas, Morten Kamphaug, Keng Siau, Kenth Engo-Monsen Jun 2024

The Next 'Deep' Thing In X To Z Marketing: An Artificial Intelligence Driven Approach, Vincent Charles, Nripendra Rana, Ilias O. Pappas, Morten Kamphaug, Keng Siau, Kenth Engo-Monsen

Research Collection School Of Computing and Information Systems

The existing body of literature indicates a growing interest in research pertaining to the influence of artificial intelligence (AI) on marketing strategies, processes, and practices. However, further studies are required to fully unravel its complete potential and the implications it holds for practical application. The aim of this special issue on “The Next ‘Deep’ Thing in X to Z Marketing: An Artificial Intelligence-Driven Approach” is to explore the next frontiers and delve into the various facets of AI-driven marketing, shedding light on cutting-edge research and practical insights that can shape the future of the field. It also focuses on novel …

Go to article

Actively Learn From Llms With Uncertainty Propagation For Generalized Category Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang Jun 2024

Actively Learn From Llms With Uncertainty Propagation For Generalized Category Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang

Research Collection School Of Computing and Information Systems

Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches tend to become overly tailored to known categories, failing to fully resolve the core issue. Hence, we propose to integrate the feedback from LLMs into an active learning paradigm. Specifically, our method innovatively employs uncertainty propagation to select data samples from high-uncertainty regions, which are then labeled using LLMs through a comparison-based prompting scheme. This not only eases the labeling task …

Go to article

Mix-Initiative Response Generation With Dynamic Prefix Tuning, Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao Jun 2024

Mix-Initiative Response Generation With Dynamic Prefix Tuning, Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao

Research Collection School Of Computing and Information Systems

Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in …

Go to article

Generalized Graph Prompt: Toward A Unification Of Pre-Training And Downstream Tasks On Graphs, Xingtong Yu, Zhenghao Liu, Yuan Fang, Et Al. Jun 2024

Generalized Graph Prompt: Toward A Unification Of Pre-Training And Downstream Tasks On Graphs, Xingtong Yu, Zhenghao Liu, Yuan Fang, Et Al.

Research Collection School Of Computing and Information Systems

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the 'pre-train, fine-tune' and 'pre-train, prompt' paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of …

Go to article

Learning Transferable Negative Prompts For Out-Of-Distribution Detection, Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng Jun 2024

Learning Transferable Negative Prompts For Out-Of-Distribution Detection, Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng

Research Collection School Of Computing and Information Systems

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current …

Go to article

Anomaly Heterogeneity Learning For Open-Set Supervised Anomaly Detection, Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang Jun 2024

Anomaly Heterogeneity Learning For Open-Set Supervised Anomaly Detection, Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang

Research Collection School Of Computing and Information Systems

Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods are trained in a closed-set setting and treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. This paper proposes to …

Go to article

Open-Vocabulary Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang Jun 2024

Open-Vocabulary Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Current video anomaly detection (VAD) approaches with weak supervisions are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to de-tect unseen anomalies given seen anomalies and normal videos. However, such a setting focuses on predicting frame anomaly scores, having no ability to recognize the specific categories of anomalies, despite the fact that this ability is essential for building more informed video surveillance systems. This paper takes a step …

Go to article

First Prev Next Last