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

Physical Sciences and Mathematics Commons™

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

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 1021 - 1050 of 7453

Full-Text Articles in Physical Sciences and Mathematics

Right To Know, Right To Refuse: Towards Ui Perception-Based Automated Fine-Grained Permission Controls For Android Apps, Vikas Kumar Malviya, Chee Wei Leow, Ashok Kasthuri, Naing Tun Yan, Lwin Khin Shar, Lingxiao Jiang Oct 2022

Right To Know, Right To Refuse: Towards Ui Perception-Based Automated Fine-Grained Permission Controls For Android Apps, Vikas Kumar Malviya, Chee Wei Leow, Ashok Kasthuri, Naing Tun Yan, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

It is the basic right of a user to know how the permissions are used within the Android app’s scope and to refuse the app if granted permissions are used for the activities other than specified use which can amount to malicious behavior. This paper proposes an approach and a vision to automatically model the permissions necessary for Android apps from users’ perspective and enable fine-grained permission controls by users, thus facilitating users in making more well-informed and flexible permission decisions for different app functionalities, which in turn improve the security and data privacy of the App and enforce apps …

Go to article

Pros: An Efficient Pattern-Driven Compressive Sensing Framework For Low-Power Biopotential-Based Wearable With On-Chip Intelligence, Nhat Pham, Hong Jia, Minh Tran, Tuan Dinh, Nam Bui, Young Kwon, Dong Ma, Phuc Nguyen, Cecilia Mascolo, Tam Vu Oct 2022

Pros: An Efficient Pattern-Driven Compressive Sensing Framework For Low-Power Biopotential-Based Wearable With On-Chip Intelligence, Nhat Pham, Hong Jia, Minh Tran, Tuan Dinh, Nam Bui, Young Kwon, Dong Ma, Phuc Nguyen, Cecilia Mascolo, Tam Vu

Research Collection School Of Computing and Information Systems

While the global healthcare market of wearable devices has been growing signi!cantly in recent years and is predicted to reach $60 billion by 2028, many important healthcare applications such as seizure monitoring, drowsiness detection, etc. have not been deployed due to the limited battery lifetime, slow response rate, and inadequate biosignal quality. This study proposes PROS, an e"cient pattern-driven compressive sensing framework for low-power biopotential-based wearables. PROS eliminates the conventional trade-o# between signal quality, response time, and power consumption by introducing tiny pattern recognition primitives and a pattern-driven compressive sensing technique that exploits the sparsity of biosignals. Specifically, we (i) …

Go to article

Locally Varying Distance Transform For Unsupervised Visual Anomaly Detection, Wen-Yan Lin, Zhonghang Liu, Siying Liu Oct 2022

Locally Varying Distance Transform For Unsupervised Visual Anomaly Detection, Wen-Yan Lin, Zhonghang Liu, Siying Liu

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection on image data is notoriously unstable. We believe this is because many classical anomaly detectors implicitly assume data is low dimensional. However, image data is always high dimensional. Images can be projected to a low dimensional embedding but such projections rely on global transformations that truncate minor variations. As anomalies are rare, the final embedding often lacks the key variations needed to distinguish anomalies from normal instances. This paper proposes a new embedding using a set of locally varying data projections, with each projection responsible for persevering the variations that distinguish a local cluster of instances from …

Go to article

What Machines Can't Do (Yet) In Real Work Settings, Thomas H. Davenport, Steven M. Miller Oct 2022

What Machines Can't Do (Yet) In Real Work Settings, Thomas H. Davenport, Steven M. Miller

Research Collection School Of Computing and Information Systems

AI systems may perform well in the research lab or under highly controlled application settings, but they still needed human help in the types of real world work settings we researched for a new book, Working With AI: Real Stories of Human-Machine Collaboration. Human workers were very much in evidence across our 30 case studies. In this article, we use those examples to illustrate our list of AI-enabled activities that still require human assistance. These are activities where organizations need to continue to invest in human capital, and where practitioners can expect job continuity for the immediate future

Go to article

Vpsl: Verifiable Privacy-Preserving Data Search For Cloud-Assisted Internet Of Things, Qiuyun Tong, Yinbin Miao, Ximeng Liu, Kim-Kwang Raymond Choo, Robert H. Deng Oct 2022

Vpsl: Verifiable Privacy-Preserving Data Search For Cloud-Assisted Internet Of Things, Qiuyun Tong, Yinbin Miao, Ximeng Liu, Kim-Kwang Raymond Choo, Robert H. Deng

Research Collection School Of Computing and Information Systems

Cloud-assisted Internet of Things (IoT) is increasingly prevalent used in various fields, such as the healthcare system. While in such a scenario, sensitive data (e.g., personal electronic medical records) can be easily revealed, which incurs potential security challenges. Thus, Symmetric Searchable Encryption (SSE) has been extensively studied due to its capability of supporting efficient search on encrypted data. However, most SSE schemes require the data owner to share the complete key with query users and take malicious cloud servers out of consideration. Seeking to address these limitations, in this paper we propose a Verifiable Privacy-preserving data Search scheme with Limited …

Go to article

Guaranteeing Timed Opacity Using Parametric Timed Model Checking, Étienne André, Didier Lime, Dylan Marinho, Jun Sun Oct 2022

Guaranteeing Timed Opacity Using Parametric Timed Model Checking, Étienne André, Didier Lime, Dylan Marinho, Jun Sun

Research Collection School Of Computing and Information Systems

Information leakage can have dramatic consequences on systems security. Among harmful information leaks, the timing information leakage occurs whenever an attacker successfully deduces confidential internal information. In this work, we consider that the attacker has access (only) to the system execution time. We address the following timed opacity problem: given a timed system, a private location and a final location, synthesize the execution times from the initial location to the final location for which one cannot deduce whether the system went through the private location. We also consider the full timed opacity problem, asking whether the system is opaque for …

Go to article

Multi-Functional Job Roles To Support Operations In A Multi-Faceted Jewel Enabled By Ai And Digital Transformation, Steven M. Miller Oct 2022

Multi-Functional Job Roles To Support Operations In A Multi-Faceted Jewel Enabled By Ai And Digital Transformation, Steven M. Miller

Research Collection School Of Computing and Information Systems

In this story, we highlight the way in which the use of AI enabled support systems, together with work process digital transformation and innovative approaches to job redesign, have combined to dramatically change the nature of the work of the front-line service staff who protect and support the facility and visitors at the world’s most iconic airport mall and lifestyle destination.

Go to article

Equivariance And Invariance Inductive Bias For Learning From Insufficient Data, Tan Wang, Qianru Sun, Sugiri Pranata, Karlekar Jayashree, Hanwang Zhang Oct 2022

Equivariance And Invariance Inductive Bias For Learning From Insufficient Data, Tan Wang, Qianru Sun, Sugiri Pranata, Karlekar Jayashree, Hanwang Zhang

Research Collection School Of Computing and Information Systems

We are interested in learning robust models from insufficient data, without the need for any externally pre-trained model checkpoints. First, compared to sufficient data, we show why insufficient data renders the model more easily biased to the limited training environments that are usually different from testing. For example, if all the training "swan" samples are "white", the model may wrongly use the "white" environment to represent the intrinsic class "swan". Then, we justify that equivariance inductive bias can retain the class feature while invariance inductive bias can remove the environmental feature, leaving only the class feature that generalizes to any …

Go to article

Class Is Invariant To Context And Vice Versa: On Learning Invariance For Out-Of-Distribution Generalization, Jiaxin Qi, Kaihua Tang, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang Oct 2022

Class Is Invariant To Context And Vice Versa: On Learning Invariance For Out-Of-Distribution Generalization, Jiaxin Qi, Kaihua Tang, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Out-Of-Distribution generalization (OOD) is all about learning invariance against environmental changes. If the context in every class is evenly distributed, OOD would be trivial because the context can be easily removed due to an underlying principle: class is invariant to context. However, collecting such a balanced dataset is impractical. Learning on imbalanced data makes the model bias to context and thus hurts OOD. Therefore, the key to OOD is context balance.We argue that the widely adopted assumption in prior work—the context bias can be directly annotated or estimated from biased class prediction—renders the context incomplete or even incorrect. In contrast, …

Go to article

Ffl: Fine Grained Fault Localization For Student Programs Via Syntactic And Semantic Reasoning, Thanh Dat Nguyen, Cong Thanh Le, Duc-Minh Luong, Van-Hai Duong, Xuan Bach Le, David Lo, Quyet-Thang Huynh Oct 2022

Ffl: Fine Grained Fault Localization For Student Programs Via Syntactic And Semantic Reasoning, Thanh Dat Nguyen, Cong Thanh Le, Duc-Minh Luong, Van-Hai Duong, Xuan Bach Le, David Lo, Quyet-Thang Huynh

Research Collection School Of Computing and Information Systems

Fault localization has been used to provide feedback for incorrect student programs since locations of faults can be a valuable hint for students about what caused their programs to crash. Unfortunately, existing fault localization techniques for student programs are limited because they usually consider either the program’s syntax or semantics alone. This motivates the new design of fault localization techniques that use both semantic and syntactical information of the program. In this paper, we introduce FFL (Fine grained Fault Localization), a novel technique using syntactic and semantic reasoning for localizing bugs in student programs. The novelty in FFL that allows …

Go to article

Transrepair: Context-Aware Program Repair For Compilation Errors, Xueyang Li, Shangqing Liu, Ruitao Feng, Guozhu Meng, Xiaofei Xie, Kai Chen, Yang Liu Oct 2022

Transrepair: Context-Aware Program Repair For Compilation Errors, Xueyang Li, Shangqing Liu, Ruitao Feng, Guozhu Meng, Xiaofei Xie, Kai Chen, Yang Liu

Research Collection School Of Computing and Information Systems

Automatically fixing compilation errors can greatly raise the productivity of software development, by guiding the novice or AI programmers to write and debug code. Recently, learning-based program repair has gained extensive attention and became the state of-the-art in practice. But it still leaves plenty of space for improvement. In this paper, we propose an end-to-end solution TransRepair to locate the error lines and create the correct substitute for a C program simultaneously. Superior to the counterpart, our approach takes into account the context of erroneous code and diagnostic compilation feedback. Then we devise a Transformer-based neural network to learn the …

Go to article

Automatic Pull Request Title Generation, Ting Zhang, Ivana Clairine Irsan, Ferdian Thung, Donggyun Han, David Lo, Lingxiao Jiang Oct 2022

Automatic Pull Request Title Generation, Ting Zhang, Ivana Clairine Irsan, Ferdian Thung, Donggyun Han, David Lo, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Pull Requests (PRs) are a mechanism on modern collaborative coding platforms, such as GitHub. PRs allow developers to tell others that their code changes are available for merging into another branch in a repository. A PR needs to be reviewed and approved by the core team of the repository before the changes are merged into the branch. Usually, reviewers need to identify a PR that is in line with their interests before providing a review. By default, PRs are arranged in a list view that shows the titles of PRs. Therefore, it is desirable to have a precise and concise …

Go to article

Accurate Generation Of Trigger-Action Programs With Domain-Adapted Sequence-To-Sequence Learning, Imam Nur Bani Yusuf, Lingxiao Jiang, David Lo Oct 2022

Accurate Generation Of Trigger-Action Programs With Domain-Adapted Sequence-To-Sequence Learning, Imam Nur Bani Yusuf, Lingxiao Jiang, David Lo

Research Collection School Of Computing and Information Systems

Trigger-action programming allows end users to write event-driven rules to automate smart devices and internet services. Users can create a trigger-action program (TAP) by specifying triggers and actions from a set of predefined functions along with suitable data fields for the functions. Many trigger-action programming platforms have emerged as the popularity grows, e.g., IFTTT, Microsoft Power Automate, and Samsung SmartThings. Despite their simplicity, composing trigger-action programs (TAPs) can still be challenging for end users due to the domain knowledge needed and enormous search space of many combinations of triggers and actions. We propose RecipeGen, a new deep learning-based approach that …

Go to article

Toward Personalized Answer Generation In E-Commerce Via Multi-Perspective Preference Modeling, Yang Deng, Yaliang Li, Wenxuan Zhang, Bolin Ding, Wai Lam Oct 2022

Toward Personalized Answer Generation In E-Commerce Via Multi-Perspective Preference Modeling, Yang Deng, Yaliang Li, Wenxuan Zhang, Bolin Ding, Wai Lam

Research Collection School Of Computing and Information Systems

Recently, Product Question Answering (PQA) on E-Commerce platforms has attracted increasing attention as it can act as an intelligent online shopping assistant and improve the customer shopping experience. Its key function, automatic answer generation for product-related questions, has been studied by aiming to generate content-preserving while question-related answers. However, an important characteristic of PQA, i.e., personalization, is neglected by existing methods. It is insufficient to provide the same “completely summarized” answer to all customers, since many customers are more willing to see personalized answers with customized information only for themselves, by taking into consideration their own preferences toward product aspects …

Go to article

Field Experiments In Operations Management, Yang Gao, Meng Li, Shujing Sun Oct 2022

Field Experiments In Operations Management, Yang Gao, Meng Li, Shujing Sun

Research Collection School Of Computing and Information Systems

While the field experiment is a powerful and well-established method to investigate causal relationships, operations management (OM) has embraced this methodology only in recent years. This paper provides a comprehensive review of the existing OM literature leveraging field experiments and serves as a one-stop guide for future application of field experiments in the OM area. We start by recapping the characteristics that distinguish field experiments from other common types of experiments and organizing the relevant OM studies by topic. Corresponding to the commonly overlooked issues in field experiment-based OM studies, we then provide a detailed roadmap, ranging from experimental design …

Go to article

Soci: A Toolkit For Secure Outsourced Computation On Integers, Bowen Zhao, Jiaming Yuan, Ximeng Liu, Yongdong Wu, Hwee Hwa Pang, Robert H. Deng Oct 2022

Soci: A Toolkit For Secure Outsourced Computation On Integers, Bowen Zhao, Jiaming Yuan, Ximeng Liu, Yongdong Wu, Hwee Hwa Pang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Secure outsourced computation is a key technique for protecting data security and privacy in the cloud. Although fully homomorphic encryption (FHE) enables computations over encrypted data, it suffers from high computation costs in order to support an unlimited number of arithmetic operations. Recently, secure computations based on interactions of multiple computation servers and partially homomorphic encryption (PHE) were proposed in the literature, which enable an unbound number of addition and multiplication operations on encrypted data more efficiently than FHE and do not add any noise to encrypted data; however, these existing solutions are either limited in functionalities (e.g., computation on …

Go to article

Softskip: Empowering Multi-Modal Dynamic Pruning For Single-Stage Referring Comprehension, Dulanga Weerakoon, Vigneshwaran Subbaraju, Tuan Tran, Archan Misra Oct 2022

Softskip: Empowering Multi-Modal Dynamic Pruning For Single-Stage Referring Comprehension, Dulanga Weerakoon, Vigneshwaran Subbaraju, Tuan Tran, Archan Misra

Research Collection School Of Computing and Information Systems

Supporting real-time referring expression comprehension (REC) on pervasive devices is an important capability for human-AI collaborative tasks. Model pruning techniques, applied to DNN models, can enable real-time execution even on resource-constrained devices. However, existing pruning strategies are designed principally for uni-modal applications, and suffer a significant loss of accuracy when applied to REC tasks that require fusion of textual and visual inputs. We thus present a multi-modal pruning model, LGMDP, which uses language as a pivot to dynamically and judiciously select the relevant computational blocks that need to be executed. LGMDP also introduces a new SoftSkip mechanism, whereby 'skipped' visual …

Go to article

Transplantfix: Graph Differencing-Based Code Transplantation For Automated Program Repair, Deheng Yang, Xiaoguang Mao, Liqian Chen, Xuezheng Xu, Yan Lei, David Lo, Jiayu He Oct 2022

Transplantfix: Graph Differencing-Based Code Transplantation For Automated Program Repair, Deheng Yang, Xiaoguang Mao, Liqian Chen, Xuezheng Xu, Yan Lei, David Lo, Jiayu He

Research Collection School Of Computing and Information Systems

Automated program repair (APR) holds the promise of aiding manual debugging activities. Over a decade of evolution, a broad range of APR techniques have been proposed and evaluated on a set of real-world bug datasets. However, while more and more bugs have been correctly fixed, we observe that the growth of newly fixed bugs by APR techniques has hit a bottleneck in recent years. In this work, we explore the possibility of addressing complicated bugs by proposing TransplantFix, a novel APR technique that leverages graph differencing-based transplantation from the donor method. The key novelty of TransplantFix lies in three aspects: …

Go to article

Lawbreaker: An Approach For Specifying Traffic Laws And Fuzzing Autonomous Vehicles, Yang Sun, Christopher M. Poskitt, Jun Sun, Yuqi Chen, Zijiang Yang Oct 2022

Lawbreaker: An Approach For Specifying Traffic Laws And Fuzzing Autonomous Vehicles, Yang Sun, Christopher M. Poskitt, Jun Sun, Yuqi Chen, Zijiang Yang

Research Collection School Of Computing and Information Systems

Autonomous driving systems (ADSs) must be tested thoroughly before they can be deployed in autonomous vehicles. High-fidelity simulators allow them to be tested against diverse scenarios, including those that are difficult to recreate in real-world testing grounds. While previous approaches have shown that test cases can be generated automatically, they tend to focus on weak oracles (e.g. reaching the destination without collisions) without assessing whether the journey itself was undertaken safely and satisfied the law. In this work, we propose LawBreaker, an automated framework for testing ADSs against real-world traffic laws, which is designed to be compatible with different scenario …

Go to article

Two Singapore Public Healthcare Ai Applications For National Screening Programs And Other Examples, Andy Wee An Ta, Han Leong Goh, Christine Ang, Lian Yeow Koh, Ken Poon, Steven M. Miller Oct 2022

Two Singapore Public Healthcare Ai Applications For National Screening Programs And Other Examples, Andy Wee An Ta, Han Leong Goh, Christine Ang, Lian Yeow Koh, Ken Poon, Steven M. Miller

Research Collection School Of Computing and Information Systems

This article explains how two AI systems have been incorporated into the everyday operations of two Singapore public healthcare nation-wide screening programs. The first example is embedded within the setting of a national level population health screening program for diabetes related eye diseases, targeting the rapidly increasing number of adults in the country with diabetes. In the second example, the AI assisted screening is done shortly after a person is admitted to one of the public hospitals to identify which inpatients—especially which elderly patients with complex conditions—have a high risk of being readmitted as an inpatient multiple times in the …

Go to article

Qvip: An Ilp-Based Formal Verification Approach For Quantized Neural Networks, Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Min Zhang, Taolue Chen, Jun Sun Oct 2022

Qvip: An Ilp-Based Formal Verification Approach For Quantized Neural Networks, Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Min Zhang, Taolue Chen, Jun Sun

Research Collection School Of Computing and Information Systems

Deep learning has become a promising programming paradigm in software development, owing to its surprising performance in solving many challenging tasks. Deep neural networks (DNNs) are increasingly being deployed in practice, but are limited on resource-constrained devices owing to their demand for computational power. Quantization has emerged as a promising technique to reduce the size of DNNs with comparable accuracy as their floating-point numbered counterparts. The resulting quantized neural networks (QNNs) can be implemented energy-efficiently. Similar to their floating-point numbered counterparts, quality assurance techniques for QNNs, such as testing and formal verification, are essential but are currently less explored. In …

Go to article

Ergo: Event Relational Graph Transformer For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao, Yan Zhang Oct 2022

Ergo: Event Relational Graph Transformer For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao, Yan Zhang

Research Collection School Of Computing and Information Systems

Document-level Event Causality Identification (DECI) aims to identify event-event causal relations in a document. Existing works usually build an event graph for global reasoning across multiple sentences. However, the edges between events have to be carefully designed through heuristic rules or external tools. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework1 for DECI, to ease the graph construction and improve it over the noisy edge issue. Different from conventional event graphs, we define a pair of events as a node and build a complete event relational graph without any prior knowledge or tools. This naturally …

Go to article

Tgdm: Target Guided Dynamic Mixup For Cross-Domain Few-Shot Learning, Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang Oct 2022

Tgdm: Target Guided Dynamic Mixup For Cross-Domain Few-Shot Learning, Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Given sufficient training data on the source domain, cross-domain few-shot learning (CD-FSL) aims at recognizing new classes with a small number of labeled examples on the target domain. The key to addressing CD-FSL is to narrow the domain gap and transferring knowledge of a network trained on the source domain to the target domain. To help knowledge transfer, this paper introduces an intermediate domain generated by mixing images in the source and the target domain. Specifically, to generate the optimal intermediate domain for different target data, we propose a novel target guided dynamic mixup (TGDM) framework that leverages the target …

Go to article

Explanation Guided Contrastive Learning For Sequential Recommendation, Lei Wang, Ee-Peng Lim, Zhiwei Liu, Tianxiang Zhao Oct 2022

Explanation Guided Contrastive Learning For Sequential Recommendation, Lei Wang, Ee-Peng Lim, Zhiwei Liu, Tianxiang Zhao

Research Collection Lee Kong Chian School Of Business

Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions. Nevertheless, the existing contrastive learning-based methods fail to ensure that the positive (or negative) sequence obtained by some random augmentation (or sequence sampling) on a given anchor user sequence remains to be semantically similar (or different). When the positive and negative sequences turn out to be false positive and false negative respectively, it may lead to degraded recommendation performance. In this work, we address the above problem by proposing Explanation Guided Augmentations …

Go to article

Artificial Intelligence, Consumers, And The Experience Economy, Hannah H. Chang, Anirban Mukherjee Oct 2022

Artificial Intelligence, Consumers, And The Experience Economy, Hannah H. Chang, Anirban Mukherjee

Research Collection Lee Kong Chian School Of Business

The term Artificial Intelligence (AI) was first used by McCarthy, Minsky, Rochester, and Shannon in a proposal for a summer research project in 1955 (Solomonoff, 1985). It is widely and commonly defined to be “the science and engineering of making intelligent machines” (McCarthy, 2006). Recent technological advances and methodological developments have made AI pervasive in new marketing offerings, ranging from self-driving cars, intelligent voice assistants such as Amazon’s Alexa, to burger-making robots at restaurants and rack-moving robots inside warehouses such as Amazon’s family of robots (Kiva, Pegasus, Xanthus) and delivery drones. There is optimism, and perhaps even over-optimism, of the …

Go to article

Using Machine Learning To Extract Insights From Consumer Data, Hannah H. Chang, Anirban Mukherjee Oct 2022

Using Machine Learning To Extract Insights From Consumer Data, Hannah H. Chang, Anirban Mukherjee

Research Collection Lee Kong Chian School Of Business

Advances in digital technology have led to the digitization of everyday activities of billions of people around the world, generating vast amounts of data on human behavior. From what people buy, to what information they search for, to how they navigate the social, digital, and physical world, human behavior can now be measured at a scale and level of precision that human history has not witnessed before. These developments have created unprecedented opportunities for those interested in understanding observable human behavior–social scientists, businesses, and policymakers—to (re)examine theoretical and substantive questions regarding people’s behavior. Moreover, technology has led to the emergence …

Go to article

Dualformer: Local-Global Stratified Transformer For Efficient Video Recognition, Yuxuan Liang, Pan Zhou, Roger Zimmermann, Shuicheng Yan Oct 2022

Dualformer: Local-Global Stratified Transformer For Efficient Video Recognition, Yuxuan Liang, Pan Zhou, Roger Zimmermann, Shuicheng Yan

Research Collection School Of Computing and Information Systems

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens. In this paper, we present a new transformer architecture termed DualFormer, which can efficiently perform space-time attention for video recognition. Concretely, DualFormer stratifies the full space-time attention into dual cascaded levels, i.e., to first learn fine-grained local interactions among nearby 3D tokens, and then to capture coarse-grained global dependencies between the query token and global pyramid contexts. Different from existing methods that apply space-time factorization or …

Go to article

Self-Promoted Supervision For Few-Shot Transformer, Bowen Dong, Pan Zhou, Shuicheng Yan, Wangmeng Zuo Oct 2022

Self-Promoted Supervision For Few-Shot Transformer, Bowen Dong, Pan Zhou, Shuicheng Yan, Wangmeng Zuo

Research Collection School Of Computing and Information Systems

The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired. In this work, we empirically find that with the same few-shot learning frameworks, e.g. MetaBaseline, replacing the widely used CNN feature extractor with a ViT model often severely impairs few-shot classification performance. Moreover, our empirical study shows that in the absence of inductive bias, ViTs often learn the low-qualified token dependencies under few-shot learning regime where only a few labeled training data are available, which largely contributes to the above performance degradation. To alleviate this issue, for the first time, we propose a simple yet effective …

Go to article

Unsupervised Video Hashing With Multi-Granularity Contextualization And Multi-Structure Preservation, Yanbin Hao, Jingru Duan, Hao Zhang, Bin Zhu, Pengyuan Zhou, Xiangnan He Oct 2022

Unsupervised Video Hashing With Multi-Granularity Contextualization And Multi-Structure Preservation, Yanbin Hao, Jingru Duan, Hao Zhang, Bin Zhu, Pengyuan Zhou, Xiangnan He

Research Collection School Of Computing and Information Systems

Unsupervised video hashing typically aims to learn a compact binary vector to represent complex video content without using manual annotations. Existing unsupervised hashing methods generally suffer from incomplete exploration of various perspective dependencies (e.g., long-range and short-range) and data structures that exist in visual contents, resulting in less discriminative hash codes. In this paper, we propose aMulti-granularity Contextualized and Multi-Structure preserved Hashing (MCMSH) method, exploring multiple axial contexts for discriminative video representation generation and various structural information for unsupervised learning simultaneously. Specifically, we delicately design three self-gating modules to separately model three granularities of dependencies (i.e., long/middle/short-range dependencies) and densely …

Go to article

Artificial Intelligence And Human Employment, Singapore Management University Sep 2022

Artificial Intelligence And Human Employment, Singapore Management University

Perspectives@SMU

AI will replace humans in repetitive tasks. Greater value can be created when it augments and complements the jobs people do

Go to article

First Prev Next Last