Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Computer Sciences (7226)
- Databases and Information Systems (2961)
- Software Engineering (1895)
- Artificial Intelligence and Robotics (1081)
- Numerical Analysis and Scientific Computing (963)
-
- Information Security (937)
- Engineering (795)
- Social and Behavioral Sciences (773)
- Graphics and Human Computer Interfaces (676)
- Business (671)
- Theory and Algorithms (454)
- Computer Engineering (410)
- Operations Research, Systems Engineering and Industrial Engineering (366)
- Programming Languages and Compilers (310)
- Communication (301)
- OS and Networks (300)
- Social Media (244)
- Public Affairs, Public Policy and Public Administration (203)
- Environmental Sciences (168)
- Data Storage Systems (164)
- Medicine and Health Sciences (163)
- Transportation (163)
- International and Area Studies (153)
- Management Information Systems (153)
- Asian Studies (151)
- Education (145)
- Technology and Innovation (126)
- E-Commerce (120)
- Finance and Financial Management (98)
- Keyword
-
- Deep learning (109)
- Machine learning (105)
- Artificial intelligence (77)
- Singapore (76)
- Social media (73)
-
- Data mining (62)
- Cloud computing (57)
- Reinforcement learning (54)
- Optimization (51)
- Security (51)
- Privacy (50)
- Twitter (49)
- Online learning (48)
- Software engineering (47)
- Visualization (46)
- Deep Learning (45)
- Empirical study (45)
- Neural networks (45)
- Task analysis (44)
- Access control (41)
- Feature extraction (41)
- Algorithms (40)
- Blockchain (39)
- Semantics (39)
- Sustainability (39)
- Classification (38)
- Android (35)
- Anomaly detection (35)
- Clustering (35)
- Collaboration (35)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (6891)
- Dissertations and Theses Collection (Open Access) (128)
- Research Collection Lee Kong Chian School Of Business (94)
- Research Collection School of Social Sciences (48)
- Research Collection College of Integrative Studies (44)
-
- Perspectives@SMU (38)
- Asian Management Insights (35)
- Research Collection Yong Pung How School Of Law (30)
- Research Collection School Of Accountancy (23)
- Research Collection School Of Economics (22)
- Dissertations and Theses Collection (15)
- SMU Press Releases (12)
- MITB Thought Leadership Series (11)
- Research@SMU: Connecting the Dots (10)
- Research Collection School of Computing and Information Systems (9)
- LARC Research Publications (7)
- Research Collection Library (6)
- Social Space (5)
- SMU Research Data (4)
- Sim Kee Boon Institute for Financial Economics (4)
- 2024 AI for Research Week (3)
- Centre for Computational Law (3)
- CMP Research (2)
- Centre for AI & Data Governance (2)
- Research Collection Office of Research (2)
- Library Events (1)
- Oral History Collection (1)
- ROSA Journal Articles and Publications (1)
- Research Collection School of Accountancy (1)
- Research@SMU Infographics (1)
- Publication Type
- File Type
Articles 1171 - 1200 of 7453
Full-Text Articles in Physical Sciences and Mathematics
Transportation-Enabled Urban Services: A Brief Discussion, Hai Wang
Transportation-Enabled Urban Services: A Brief Discussion, Hai Wang
Research Collection School Of Computing and Information Systems
Nearly 55% of the world's population lives in urban areas or cities, and is expected to rise above 70% over the coming decades. Rapid urbanization brings steadily more residents and a growing freelancing workforce into cities. The developments of city infrastructure and technologies—for instance, mobile location tracking and computing, autonomous and connected vehicles, wearable devices, robotics and robots, smart appliances, biometric authentication, various internet-of-things devices, and smart monitoring systems—are creating numerous opportunities and inspiring innovative and emerging urban services. Among these innovations, complex systems of urban transportation and logistics have embraced advances in technologies and, consequently, been significantly reshaped (Agatz …
Flavor-Videos: Enhancing The Flavor Perception Of Food While Eating With Videos, Meetha Nesam James, Nimesha Ranasinghe, Anthony Tang, Lora Oehlberg
Flavor-Videos: Enhancing The Flavor Perception Of Food While Eating With Videos, Meetha Nesam James, Nimesha Ranasinghe, Anthony Tang, Lora Oehlberg
Research Collection School Of Computing and Information Systems
People are typically involved in different activities while eating, particularly when eating alone, such as watching television or playing games on their phones. Previous research in Human-Food Interaction (HFI) has primarily focused on studying people’s motivation and analyzing of the media content watched while eating. However, their impact on human behavioral and cognitive processes, particularly flavor perception and its attributes, remains underexplored. We present a user study to investigate the influence of six types of videos, including mukbang – a new food video genre, on flavor perceptions (taste sensations, liking, and emotions) while eating plain white rice. Our findings revealed …
Deep Learning For Person Re-Identification: A Survey And Outlook, Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi
Deep Learning For Person Re-Identification: A Survey And Outlook, Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID …
Decomposing Generation Networks With Structure Prediction For Recipe Generation, Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao
Decomposing Generation Networks With Structure Prediction For Recipe Generation, Hao Wang, Guosheng Lin, Steven C. H. Hoi, Chunyan Miao
Research Collection School Of Computing and Information Systems
Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality. Different from the image captioning task, where the captions usually have one sentence, cooking instructions contain multiple sentences and have obvious structures. To help the model capture the recipe structure and avoid missing some cooking details, we propose a novel framework: Decomposing Generation Networks (DGN) with structure prediction, to get more structured and complete recipe generation outputs. Specifically, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: …
Deep Learning For Anomaly Detection, Guansong Pang, Charu Aggarwal, Chunhua Shen, Nicu Sebe
Deep Learning For Anomaly Detection, Guansong Pang, Charu Aggarwal, Chunhua Shen, Nicu Sebe
Research Collection School Of Computing and Information Systems
A nomaly detection aims at identifying data points which are rare or significantly different from the majority of data points. Many techniques are explored to build highly efficient and effective anomaly detection systems, but they are confronted with many difficulties when dealing with complex data, such as failing to capture intricate feature interactions or extract good feature representations. Deep-learning techniques have shown very promising performance in tackling different types of complex data in a broad range of tasks/problems, including anomaly detection. To address this new trend, we organized this Special Issue on Deep Learning for Anomaly Detection to cover the …
Consensus Formation On Heterogeneous Networks, Edoardo Fadda, Junda He, Claudia J. Tessone, Paolo Barucca
Consensus Formation On Heterogeneous Networks, Edoardo Fadda, Junda He, Claudia J. Tessone, Paolo Barucca
Research Collection School Of Computing and Information Systems
Reaching consensus-a macroscopic state where the system constituents display the same microscopic state-is a necessity in multiple complex socio-technical and techno-economic systems: their correct functioning ultimately depends on it. In many distributed systems-of which blockchain-based applications are a paradigmatic example-the process of consensus formation is crucial not only for the emergence of a leading majority but for the very functioning of the system. We build a minimalistic network model of consensus formation on blockchain systems for quantifying how central nodes-with respect to their average distance to others-can leverage on their position to obtain competitive advantage in the consensus process. We …
Hu-Fu: Efficient And Secure Spatial Queries Over Data Federation, Yongxin Tong, Xuchen Pan, Yuxiang Zeng, Yexuan Shi, Chunbo Xue, Zimu Zhou, Xiaofei Zhang, Lei Chen, Yi Xu, Ke Xu, Weifeng Lv
Hu-Fu: Efficient And Secure Spatial Queries Over Data Federation, Yongxin Tong, Xuchen Pan, Yuxiang Zeng, Yexuan Shi, Chunbo Xue, Zimu Zhou, Xiaofei Zhang, Lei Chen, Yi Xu, Ke Xu, Weifeng Lv
Research Collection School Of Computing and Information Systems
Data isolation has become an obstacle to scale up query processing over big data, since sharing raw data among data owners is often prohibitive due to security concerns. A promising solution is to perform secure queries over a federation of multiple data owners leveraging secure multi-party computation (SMC) techniques, as evidenced by recent federation work over relational data. However, existing solutions are highly inefficient on spatial queries due to excessive secure distance operations for query processing and their usage of general-purpose SMC libraries for secure operation implementation. In this paper, we propose Hu-Fu, the first system for efficient and secure …
Mems Ultrasonic Transducers For Safe, Low-Power And Portable Eye-Blinking Monitoring, Sheng Sun, Jianyuan Wang, Menglun Zhang, Yuan Ning, Dong Ma, Yi Yuan, Pengfei Niu, Zhicong Rong, Zhuochen Wang, Wei Pang
Mems Ultrasonic Transducers For Safe, Low-Power And Portable Eye-Blinking Monitoring, Sheng Sun, Jianyuan Wang, Menglun Zhang, Yuan Ning, Dong Ma, Yi Yuan, Pengfei Niu, Zhicong Rong, Zhuochen Wang, Wei Pang
Research Collection School Of Computing and Information Systems
Eye blinking is closely related to human physiology and psychology. It is an effective method of communication among people and can be used in human–machine interactions. Existing blink monitoring methods include video-oculography, electro-oculograms and infrared oculography. However, these methods suffer from uncomfortable use, safety risks, limited reliability in strong light or dark environments, and infringed informational security. In this paper, we propose an ultrasound-based portable approach for eye-blinking activity monitoring. Low-power pulse-echo ultrasound featuring biosafety is transmitted and received by microelectromechanical system (MEMS) ultrasonic transducers seamlessly integrated on glasses. The size, weight and power consumption of the transducers are 2.5 …
Information Sources, Perceived Personal Experience, And Climate Change Beliefs, Sonny Rosenthal
Information Sources, Perceived Personal Experience, And Climate Change Beliefs, Sonny Rosenthal
Research Collection College of Integrative Studies
This study proposes and tests a model of serial mediation based on the norm activation model and value-belief-norm theory. It argues that beliefs about climate change are related to perceived personal experience, which is related to the use of different information sources. Structural equation modeling of survey data from 1084 adult residents of Singapore found mixed support for three hypotheses. Results showed that perceived personal experience of climate change was related to the use of traditional media (β = 0.20), social media (β = 0.16), and interpersonal sources (β = 0.13), but not institutional sources. Perceived personal experience of climate …
Challenges For Inclusion In Software Engineering: The Case Of The Emerging Papua New Guinean Society, Raula Kula, Christoph Treude, Hideaki Hata, Sebastian Baltes, Igor Steinmacher, Marco Gerosa, Winifred Kula Amini
Challenges For Inclusion In Software Engineering: The Case Of The Emerging Papua New Guinean Society, Raula Kula, Christoph Treude, Hideaki Hata, Sebastian Baltes, Igor Steinmacher, Marco Gerosa, Winifred Kula Amini
Research Collection School Of Computing and Information Systems
Software plays a central role in modern societies, with its high economic value and potential for advancing societal change. In this paper, we characterise challenges and opportunities for a country progressing towards entering the global software industry, focusing on Papua New Guinea (PNG). By hosting a Software Engineering workshop, we conducted a qualitative study by recording talks (n=3), employing a questionnaire (n=52), and administering an in-depth focus group session with local actors (n=5). Based on a thematic analysis, we identified challenges as barriers and opportunities for the PNG software engineering community. We also discuss the state of practices and how …
Do-Gan: A Double Oracle Framework For Generative Adversarial Networks, Aye Phyu Phye Aung, Xinrun Wang, Runsheng Yu, Bo An, Senthilnath Jayavelu, Xiaoli Li
Do-Gan: A Double Oracle Framework For Generative Adversarial Networks, Aye Phyu Phye Aung, Xinrun Wang, Runsheng Yu, Bo An, Senthilnath Jayavelu, Xiaoli Li
Research Collection School Of Computing and Information Systems
In this paper, we propose a new approach to train Gen-erative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discrim-inator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response or-acles. We then compute the …
Differential Cost Analysis With Simultaneous Potentials And Anti-Potentials, Dorde Zikelic, Bor-Yuh Evan Chang, Pauline Bolignano, Franco Raimondi
Differential Cost Analysis With Simultaneous Potentials And Anti-Potentials, Dorde Zikelic, Bor-Yuh Evan Chang, Pauline Bolignano, Franco Raimondi
Research Collection School Of Computing and Information Systems
We present a novel approach to differential cost analysis that, given a program revision, attempts to statically bound the difference in resource usage, or cost, between the two program versions. Differential cost analysis is particularly interesting because of the many compelling applications for it, such as detecting resource-use regressions at code-review time or proving the absence of certain side-channel vulnerabilities. One prior approach to differential cost analysis is to apply relational reasoning that conceptually constructs a product program on which one can over-approximate the difference in costs between the two program versions. However, a significant challenge in any relational approach …
A Simple Data Mixing Prior For Improving Self-Supervised Learning, Sucheng Ren, Huiyu Wang, Zhengqi Gao, Shengfeng He, Alan Yuille, Yuyin Zhou, Cihang Xie
A Simple Data Mixing Prior For Improving Self-Supervised Learning, Sucheng Ren, Huiyu Wang, Zhengqi Gao, Shengfeng He, Alan Yuille, Yuyin Zhou, Cihang Xie
Research Collection School Of Computing and Information Systems
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same source images are intrinsically related to each other, we hereby propose SDMP, short for Simple Data Mixing Prior, to capture this straightforward yet essential prior, and position such mixed images as additional positive pairs to facilitate self-supervised representation learning. Our experiments verify that the proposed SDMP enables data mixing to help a set of self-supervised learning frameworks (e.g., MoCo) achieve better accuracy and out-of-distribution …
Rhythmedge: Enabling Contactless Heart Rate Estimation On The Edge, Zahid Hasan, Emon Dey, Sreenivasan Ramasamy Ramamurthy, Nirmalya Roy, Archan Misra
Rhythmedge: Enabling Contactless Heart Rate Estimation On The Edge, Zahid Hasan, Emon Dey, Sreenivasan Ramasamy Ramamurthy, Nirmalya Roy, Archan Misra
Research Collection School Of Computing and Information Systems
The primary contribution of this paper is designing and prototyping a real-time edge computing system, RhythmEdge, that is capable of detecting changes in blood volume from facial videos (Remote Photoplethysmography; rPPG), enabling cardio-vascular health assessment instantly. The benefits of RhythmEdge include non-invasive measurement of cardiovascular activity, real-time system operation, inexpensive sensing components, and computing. RhythmEdge captures a short video of the skin using a camera and extracts rPPG features to estimate the Photoplethysmography (PPG) signal using a multi-task learning framework while offloading the edge computation. In addition, we intelligently apply a transfer learning approach to the multi-task learning framework to …
Learning To Solve Routing Problems Via Distributionally Robust Optimization, Jiang Yuan, Yaoxin Wu, Zhiguang Cao
Learning To Solve Routing Problems Via Distributionally Robust Optimization, Jiang Yuan, Yaoxin Wu, Zhiguang Cao
Research Collection School Of Computing and Information Systems
Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability. In this paper, we exploit group distributionally robust optimization (group DRO) to tackle this issue, where we jointly optimize the weights for different groups of distributions and the parameters for the deep model in an interleaved manner during training. We also design a module based on convolutional neural network, which allows the deep model to learn more informative latent pattern among the nodes. We evaluate the proposed approach on two types of wellknown deep models including GCN …
Officers: Operational Framework For Intelligent Crime-And-Emergency Response Scheduling, Jonathan David Chase, Siong Thye Goh, Tran Phong, Hoong Chuin Lau
Officers: Operational Framework For Intelligent Crime-And-Emergency Response Scheduling, Jonathan David Chase, Siong Thye Goh, Tran Phong, Hoong Chuin Lau
Research Collection School Of Computing and Information Systems
In the quest to achieve better response times in dense urban environments, law enforcement agencies are seeking AI-driven planning systems to inform their patrol strategies. In this paper, we present a framework, OFFICERS, for deployment planning that learns from historical data to generate deployment schedules on a daily basis. We accurately predict incidents using ST-ResNet, a deep learning technique that captures wide-ranging spatio-temporal dependencies, and solve a large-scale optimization problem to schedule deployment, significantly improving its scalability through a simulated annealing solver. Methodologically, our approach outperforms our previous works where prediction was done using Generative Adversarial Networks, and optimization was …
Multi-View Scheduling Of Onboard Live Video Analytics To Minimize Frame Processing Latency, Shengzhong Liu, Tianshi Wang, Hongpeng Guo, Xinzhe Fu, Philip David, Maggie Wigness, Archan Misra, Tarek Abdelzaher
Multi-View Scheduling Of Onboard Live Video Analytics To Minimize Frame Processing Latency, Shengzhong Liu, Tianshi Wang, Hongpeng Guo, Xinzhe Fu, Philip David, Maggie Wigness, Archan Misra, Tarek Abdelzaher
Research Collection School Of Computing and Information Systems
This paper presents a real-time multi-view scheduling framework for DNN-based live video analytics at the edge to minimize frame processing latency. The work is motivated by applications where a higher frame rate is important, not to miss actions of interest. Examples include defense, border security, and intruder detection applications where sensors (in this paper, cameras) are deployed to monitor key roads, chokepoints, or passageways to identify events of interest (and intervene in real-time). Supporting a higher frame rate entails lowering frame processing latency. We assume that multiple cameras are deployed with partially overlapping views. Each camera has access to limited …
A Practical Comparison Of Quantum And Classical Leaderless Consensus, Paul Robert Griffin, Dimple Mevada
A Practical Comparison Of Quantum And Classical Leaderless Consensus, Paul Robert Griffin, Dimple Mevada
Research Collection School Of Computing and Information Systems
Quantum computing is coming of age and being explored in many business areas for either solving difficult problems or improving business processes. Distributed ledger technology (DLT) is now embedded in many businesses and continues to mature. Consensus, at the heart of DLTs, has practical scaling issues and, as we move into needing bigger datasets, bigger networks and more security, the problem is ever increasing. Consensus agreement is a non-deterministic problem which is a good match to quantum computers due to the probabilistic nature of quantum phenomena. In this paper, we show that quantum nodes entangled in a variety of network …
You Have Earned A Trophy: Characterize In-Game Achievements And Their Completions, Haewoon Kwak
You Have Earned A Trophy: Characterize In-Game Achievements And Their Completions, Haewoon Kwak
Research Collection School Of Computing and Information Systems
Achievement systems have been actively adopted in gaming platforms to maintain players’ interests. Among them, trophies in PlayStation games are one of the most successful achievement systems. While the importance of trophy design has been casually discussed in many game developers’ forums, there has been no systematic study of the historical dataset of trophies yet. In this work, we construct a complete dataset of PlayStation games and their trophies and investigate them from both the developers’ and players’ perspectives.
Class Re-Activation Maps For Weakly-Supervised Semantic Segmentation, Zhaozheng Chen, Tan Wang, Xiongwei Wu, Xian-Sheng Hua, Hanwang Zhang, Qianru Sun
Class Re-Activation Maps For Weakly-Supervised Semantic Segmentation, Zhaozheng Chen, Tan Wang, Xiongwei Wu, Xian-Sheng Hua, Hanwang Zhang, Qianru Sun
Research Collection School Of Computing and Information Systems
Extracting class activation maps (CAM) is arguably the most standard step of generating pseudo masks for weakly supervised semantic segmentation (WSSS). Yet, we find that the crux of the unsatisfactory pseudo masks is the binary cross-entropy loss (BCE) widely used in CAM. Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field. To this end, we introduce an embarrassingly simple yet surprisingly effective method: Reactivating the converged CAM with BCE by using softmax crossentropy loss (SCE), dubbed ReCAM. Given an image, we use CAM to …
Catching Both Gray And Black Swans: Open-Set Supervised Anomaly Detection, Choubo Ding, Guansong Pang, Chunhua Shen
Catching Both Gray And Black Swans: Open-Set Supervised Anomaly Detection, Choubo Ding, Guansong Pang, Chunhua Shen
Research Collection School Of Computing and Information Systems
Despite most existing anomaly detection studies assume the availability of normal training samples only, a few labeled anomaly examples are often available in many real-world applications, such as defect samples identified during random quality inspection, lesion images confirmed by radiologists in daily medical screening, etc. These anomaly examples provide valuable knowledge about the application-specific abnormality, enabling significantly improved detection of similar anomalies in some recent models. However, those anomalies seen during training often do not illustrate every possible class of anomaly, rendering these models ineffective in generalizing to unseen anomaly classes. This paper tackles open-set supervised anomaly detection, in which …
Revisiting Local Descriptor For Improved Few-Shot Classification, Jun He, Richang Hong, Xueliang Liu, Mingliang Xu, Qianru Sun
Revisiting Local Descriptor For Improved Few-Shot Classification, Jun He, Richang Hong, Xueliang Liu, Mingliang Xu, Qianru Sun
Research Collection School Of Computing and Information Systems
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and more complex classifiers that measure similarities between query and support images but left the importance of feature embeddings seldom explored. We show that the reliance on sophisticated classifiers is not necessary, and a simple classifier applied directly to improved feature embeddings can instead outperform most of the leading methods in the literature. To this end, we present a new method, named DCAP, for few-shot classification, in which …
Generative Flows With Invertible Attentions, Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool
Generative Flows With Invertible Attentions, Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool
Research Collection School Of Computing and Information Systems
Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while it has made breakthroughs in other domains. To fill the gap, this paper introduces two types of invertible attention mechanisms, i.e., map-based and transformer-based attentions, for both unconditional and conditional generative flows. The key idea is to exploit a masked scheme of these two attentions to learn long-range data dependencies in the context of generative flows. The masked scheme allows for invertible attention modules with tractable Jacobian determinants, …
Blocklens: Visual Analytics Of Student Coding Behaviors In Block-Based Programming Environments., Sean Tung, Huan Wei, Haotian Li, Yong Wang, Meng Xia, Huamin. Qu
Blocklens: Visual Analytics Of Student Coding Behaviors In Block-Based Programming Environments., Sean Tung, Huan Wei, Haotian Li, Yong Wang, Meng Xia, Huamin. Qu
Research Collection School Of Computing and Information Systems
Block-based programming environments have been widely used to introduce K-12 students to coding. To guide students effectively, instructors and platform owners often need to understand behaviors like how students solve certain questions or where they get stuck and why. However, it is challenging for them to effectively analyze students’ coding data. To this end, we propose BlockLens, a novel visual analytics system to assist instructors and platform owners in analyzing students’ block-based coding behaviors, mistakes, and problem-solving patterns. BlockLens enables the grouping of students by question progress and performance, identification of common problem-solving strategies and pitfalls, and presentation of insights …
Shunted Self-Attention Via Multi-Scale Token Aggregation, Sucheng Ren, Daquan Zhou, Shengfeng He, Jiashi Feng, Xinchao Wang
Shunted Self-Attention Via Multi-Scale Token Aggregation, Sucheng Ren, Daquan Zhou, Shengfeng He, Jiashi Feng, Xinchao Wang
Research Collection School Of Computing and Information Systems
Recent Vision Transformer (ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to its competence in modeling long-range dependencies of image patches or tokens via self-attention. These models, however, usually designate the similar receptive fields of each token feature within each layer. Such a constraint inevitably limits the ability of each self-attention layer in capturing multi-scale features, thereby leading to performance degradation in handling images with multiple objects of different scales. To address this issue, we propose a novel and generic strategy, termed shunted selfattention (SSA), that allows ViTs to model the attentions at hybrid scales per …
Co-Advise: Cross Inductive Bias Distillation, Sucheng Ren, Zhengqi Gao, Tiany Hua, Zihui Xue, Yonglong Tian, Shengfeng He, Hang Zhao
Co-Advise: Cross Inductive Bias Distillation, Sucheng Ren, Zhengqi Gao, Tiany Hua, Zihui Xue, Yonglong Tian, Shengfeng He, Hang Zhao
Research Collection School Of Computing and Information Systems
The inductive bias of vision transformers is more relaxed that cannot work well with insufficient data. Knowledge distillation is thus introduced to assist the training of transformers. Unlike previous works, where merely heavy convolution-based teachers are provided, in this paper, we delve into the influence of models inductive biases in knowledge distillation (e.g., convolution and involution). Our key observation is that the teacher accuracy is not the dominant reason for the student accuracy, but the teacher inductive bias is more important. We demonstrate that lightweight teachers with different architectural inductive biases can be used to co-advise the student transformer with …
Metaformer Is Actually What You Need For Vision, Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan
Metaformer Is Actually What You Need For Vision, Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan
Research Collection School Of Computing and Information Systems
Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe …
Mlp-3d: A Mlp-Like 3d Architecture With Grouped Time Mixing, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei
Mlp-3d: A Mlp-Like 3d Architecture With Grouped Time Mixing, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei
Research Collection School Of Computing and Information Systems
Convolutional Neural Networks (CNNs) have been re-garded as the go-to models for visual recognition. More re-cently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing these newly-minted networks for video recognition due to the large variations and complexities in video data. In this paper, we present MLP-3D networks, a novel MLP-like 3D architecture for video recognition. Specifically, the architecture consists of MLP-3D blocks, where each block contains one MLP applied across tokens (i.e., token-mixing MLP) and one MLP applied independently to each token (i.e., channel MLP). …
Learnings From A Pilot Hybrid Question Answering System: Cqas: Case Study Based On A Singapore Government Agency's Customer Service Centre, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh
Learnings From A Pilot Hybrid Question Answering System: Cqas: Case Study Based On A Singapore Government Agency's Customer Service Centre, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh
Research Collection School Of Computing and Information Systems
The Singapore Government first released their digital government blueprint in 2018 with the key message for all their agencies to be "digital to the core and served with heart". With this push, agencies are moving towards human-centric digital services, especially for individual citizens. During COVID-19, Singapore government agencies introduced many COVID-19 digital initiatives resulting in more incoming inquiries from citizens to respective agencies. This surge in inquiries created the challenge on the agencies' end to meet service level agreements. One widely adopted solution is the use of chatbot technology that directly interfaces with the customer. However, several organisations have faced …
Joint Pricing And Matching For City-Scale Ride Pooling, Sanket Shah, Meghna Lowalekar, Pradeep Varakantham
Joint Pricing And Matching For City-Scale Ride Pooling, Sanket Shah, Meghna Lowalekar, Pradeep Varakantham
Research Collection School Of Computing and Information Systems
Central to efficient ride-pooling are two challenges: (1) how to `price' customers' requests for rides, and (2) if the customer agrees to that price, how to best `match' these requests to drivers. While both of them are interdependent, each challenge's individual complexity has meant that, historically, they have been decoupled and studied individually. This paper creates a framework for batched pricing and matching in which pricing is seen as a meta-level optimisation over different possible matching decisions. Our key contributions are in developing a variant of the revenue-maximizing auction corresponding to the meta-level optimization problem, and then providing a scalable …