Lei Bai

Lei Bai
The University of Sydney

Doctor of Philosophy

About

48
Publications
7,803
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
306
Citations
Introduction
Lei Bai is a Postdoctoral Research Fellow at School of Electrical and Information Engineering, the University of Sydney. His research interests lay in Deep Learning and Spatial-temporal Data Mining with focusing applications on Smart Cities, Human Pattern Recognition (e.g. EEG, Activity) and IoT Analytics.

Publications

Publications (48)
Conference Paper
Full-text available
Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand over multiple time horizons is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger demand prediction based on a graph...
Preprint
Full-text available
Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. I...
Preprint
Full-text available
Contrastive-based self-supervised learning methods achieved great success in recent years. However, self-supervision requires extremely long training epochs (e.g., 800 epochs for MoCo v3) to achieve promising results, which is unacceptable for the general academic community and hinders the development of this topic. This work revisits the momentum-...
Preprint
Full-text available
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest. However, existing tracking approaches rely on customized sub-modules and need prior knowledge for architecture selection, hindering the tracking development in a more general system. This paper presents a Simplif...
Article
Motion modeling is crucial in modern action recognition methods. As motion dynamics like moving tempos and action amplitude may vary a lot in different video clips, it poses great challenge on adaptively covering proper motion information. To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversifi...
Article
Multiple modalities can provide rich semantic information; and exploiting such information will normally lead to better performance compared with the single-modality counterpart. However, it is not easy to devise an effective cross-modal fusion structure due to the variations of feature dimensions and semantics, especially when the inputs even come...
Preprint
Considering the multimodal nature of transport systems and potential cross-modal correlations, there is a growing trend of enhancing demand forecasting accuracy by learning from multimodal data. These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different instituti...
Article
Metro origin-destination prediction is a crucial yet challenging time-series analysis task in intelligent transportation systems, which aims to accurately forecast two specific types of cross-station ridership, i.e., Origin-Destination (OD) one and Destination-Origin (DO) one. However, complete OD matrices of previous time intervals can not be obta...
Preprint
Full-text available
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested o...
Preprint
Full-text available
Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative learning without sharing raw data. Despite great success, FL's performance is limited for multiple sclerosis (MS) lesion segmentation tasks, due to variance in lesion characteristics imparted by different scanners and acquisition par...
Article
Understanding and forecasting mobility patterns and travel demand are fundamental and critical to efficient transport infrastructure planning and service operation. However, most existing studies focused on deterministic demand estimation/prediction/analytics. Differently, this study provides confidence interval based demand forecasting, which can...
Preprint
Full-text available
Pedestrian counting is a fundamental tool for understanding pedestrian patterns and crowd flow analysis. Existing works (e.g., image-level pedestrian counting, crossline crowd counting et al.) either only focus on the image-level counting or are constrained to the manual annotation of lines. In this work, we propose to conduct the pedestrian counti...
Preprint
Trajectory forecasting is critical for autonomous platforms to make safe planning and actions. Currently, most trajectory forecasting methods assume that object trajectories have been extracted and directly develop trajectory predictors based on the ground truth trajectories. However, this assumption does not hold in practical situations. Trajector...
Preprint
The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervised counterparts. This paper revisits this phenomenon and sheds new light on understanding the transferability gap between unsupervised and supervised pretraining from a m...
Article
Predicting consumers’ purchasing behaviors is critical for targeted advertisement and sales promotion in e-commerce. Human faces are an invaluable source of information for gaining insights into consumer personality and behavioral traits. However, consumer’s faces are largely unexplored in previous research, and the existing face-related studies fo...
Article
Travel demand forecasting is useful for both trip and service planning, and thus is of great importance. Most existing studies focus on demand forecasting for a single mode, while much less attention has been paid to multimodal demand forecasting. This paper develops a multimodal demand forecasting approach, which can learn and utilize information/...
Preprint
Full-text available
This paper studies the task of estimating the 3D human poses of multiple persons from multiple calibrated camera views. Following the top-down paradigm, we decompose the task into two stages, i.e. person localization and pose estimation. Both stages are processed in coarse-to-fine manners. And we propose three task-specific graph neural networks fo...
Preprint
Full-text available
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the attention maps among different transformer layers are redundant. Based on the observations above, we propose a...
Preprint
Full-text available
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image recognition. However, the transformer is designed for NLP tasks and thus could be sub-optimal when directly used for...
Preprint
Metro origin-destination prediction is a crucial yet challenging task for intelligent transportation management, which aims to accurately forecast two specific types of cross-station ridership, i.e., Origin-Destination (OD) one and Destination-Origin (DO) one. However, complete OD matrices of previous time intervals can not be obtained immediately...
Article
The strong demand of autonomous driving in the industry has led to vigorous interest in 3D object detection and resulted in many excellent 3D object detection algorithms. However, the vast majority of algorithms only model single-frame data, ignoring the temporal clue in video sequence. In this work, we propose a new transformer, called Temporal-Ch...
Article
This study examines the potential of using smart card data in public transit systems to infer attributes of travelers, thereby facilitating a more user-centered public transport service design while reducing the use of expensive and time-consuming travel surveys. This is challenging since travel behaviors vary significantly over the population, spa...
Article
Supply–demand imbalance poses significant challenges to transportation systems such as taxis and shared vehicles (cars and bikes) and leads to excessive delays, income loss, and energy consumption. Accurate prediction of passenger demands is an essential step towards rescheduling resources to resolve the above challenges. However, existing work can...
Preprint
Full-text available
This study examines the potential of using smart card data in public transit systems to infer attributes of travelers, thereby facilitating a more user-centered public transport service design while reducing the use of expensive and time-consuming travel surveys. This is challenging since travel behaviors vary significantly over the population, spa...
Preprint
The strong demand of autonomous driving in the industry has lead to strong interest in 3D object detection and resulted in many excellent 3D object detection algorithms. However, the vast majority of algorithms only model single-frame data, ignoring the temporal information of the sequence of data. In this work, we propose a new transformer, called...
Preprint
Full-text available
Understanding and forecasting mobility patterns and travel demand are fundamental and critical to efficient transport infrastructure planning and service operation. However , most existing studies focused on deterministic demand estimation/prediction/analytics. Differently, this study provides confidence interval based demand forecasting, which can...
Preprint
Accurate demand forecasting of different public transport modes(e.g., buses and light rails) is essential for public service operation.However, the development level of various modes often varies sig-nificantly, which makes it hard to predict the demand of the modeswith insufficient knowledge and sparse station distribution (i.e.,station-sparse mod...
Preprint
Full-text available
It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this work, we propose a novel end-to-end knowledge directed adversarial learning framework, which portrays the cla...
Preprint
Full-text available
Predicting consumers' purchasing behaviors is critical for targeted advertisement and sales promotion in e-commerce. Human faces are an invaluable source of information for gaining insights into consumer personality and behavioral traits. However, consumer's faces are largely unexplored in previous research, and the existing face-related studies fo...
Article
Full-text available
Human activity recognition (HAR) plays an irreplaceable role in various applications and has been a prosperous researchtopic for years. Recent studies show significant progress in feature extraction (i.e., data representation) using deep learningtechniques. However, they face significant challenges in capturing multi-modal spatial-temporal patterns...
Chapter
Full-text available
Identifying patterns and detecting irregularities regarding individual mobility in public transport system is crucial for transport planning and law enforcement applications (e.g., fraudulent behavior). In this context, most of recent approaches exploit similarity learning through comparing spatial-temporal patterns between normal and irregular rec...
Chapter
Human Activity Recognition (HAR) plays an irreplaceable role in various applications such as security, gaming, and assisted living. Recent studies introduce deep learning to mitigate the manual feature extraction (i.e., data representation) efforts and achieve high accuracy. However, there are still challenges in learning accurate representations f...
Preprint
Most current studies on survey analysis and risk tolerance modelling lack professional knowledge and domain-specific models. Given the effectiveness of generative adversarial learning in cross-domain information, we design an Asymmetric cross-Domain Generative Adversarial Network (ADGAN) for domain scale inequality. ADGAN utilizes the information-s...
Article
Compared with individual recommendation, recommending services to a group of users is more complicated because of various users' preference should be considered and introduces new challenging such as fairness, which has never been well studied in current works. In this paper, we propose a novel recommendation scheme called PFGR, which combines a pr...
Preprint
Full-text available
Identifying patterns and detecting irregularities regarding individual mobility in public transport system is crucial for transport planning and operation, and also for other law enforcement applications (e.g., fraudulent behavior). In this context, most of recent approaches exploit similarity learning through comparing spatial-temporal patterns be...
Chapter
Full-text available
This study examines the potential of the smart card data in public transit systems to infer passengers’ demographic attributes, thereby enabling a human-centered public transport service design while reducing the use of expensive and time-consuming travel surveys. This is challenging since travel behaviors vary significantly over the population, sp...
Conference Paper
Full-text available
Online ride-sharing platforms have become a critical part of the urban transportation system. Accurately recommending hotspots to drivers in such platforms is essential to help drivers find passengers and improve users' experience, which calls for efficient passenger demand prediction strategy. However, predicting multi-step passenger demand is cha...
Preprint
Full-text available
Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand over multiple time horizons is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger demand prediction based on a graph...
Chapter
Full-text available
Accurate prediction of passenger demands for taxis is vital for reducing the waiting time of passengers and drivers in large cities as we move towards smart transportation systems. However, existing works are limited in fully utilizing multi-modal features. First, these models either include excessive data from weakly correlated regions or neglect...
Preprint
Full-text available
With the widespread adoption of Internet of Things (IoT), billions of everyday objects are being connected to the Internet. Effective management of these devices to support reliable, secure and high quality applications becomes challenging due to the scale. As one of the key cornerstones of IoT device management, automatic cross-device classificati...

Network

Cited By

Projects

Projects (3)
Project
Improve the intelligence of the Internet of Things by analyzing IoT data streams