1st Workshop on Automated Spatial and Temporal Anomaly Detection (ASTAD)

Overview

Anomalies and outliers in visual data can significantly impact the performance and reliability of computer vision systems. As the applications of computer vision continue to grow across various domains, the need for robust and efficient anomaly detection techniques becomes paramount. This workshop aims to bring together researchers, industry experts, and practitioners to explore the latest advancements in automated anomaly detection methods specifically tailored for computer vision tasks. The primary objective of this workshop is to provide a platform for researchers to share and discuss their cutting-edge research in the field of anomaly detection in computer vision. We seek to foster collaboration, encourage knowledge exchange, and promote the development of novel approaches to tackle the challenges posed by anomalies in visual data. The expected outcome of this workshop is to foster a vibrant exchange of knowledge and ideas among researchers and practitioners in the field. Through insightful presentations, discussions, and interactive sessions, participants will gain a comprehensive understanding of cutting-edge AI-based methodologies for anomaly detection in computer vision. The workshop aims to encourage collaborations, inspire new research directions, and promote the development of innovative solutions to address real-world challenges in anomaly detection. As a result, attendees will leave the workshop equipped with valuable insights and practical tools that will contribute to advancements in anomaly detection techniques, ultimately leading to more robust and reliable computer vision systems across various domains.

Leman Akoglu

Carnegie Mellon University

Dr. Akoglu is the Heinz College Dean’s Associate Professor at Carnegie Mellon University’s Heinz College of Information Systems and Public Policy. She also hold courtesy appointments at the Machine Learning Department (MLD) and the Computer Science Department (CSD) of School of Computer Science (SCS). At Heinz, she directs the Data Analytics Techniques Algorithms (DATA) Lab. Her research interests are broadly in data mining, graph mining, machine learning, and knowledge discovery, with specific focus on anOmaLiEs—identifying and characterizing ‘what stands out’ in large-scale, time-varying, multi-modal data sources through scalable computational methods.

Stephan Mandt

University of California, Irvine

Stephan Mandt is an Associate Professor of Computer Science and Statistics at the University of California, Irvine. His research centers on deep generative modeling, uncertainty quantification, neural data compression, and AI for science. Previously, he led the machine learning group at Disney Research in Pittsburgh and Los Angeles and held postdoctoral positions at Princeton and Columbia University.

Guansong Pang

Singapore Management University

Dr. Guansong Pang is an Assistant Professor at the School of Computing and Information Systems, Singapore Management University, specializing in anomaly detection, machine learning, and data mining. His research focuses on developing innovative algorithms for anomaly detection, outlier detection, and self-supervised learning, with applications across cybersecurity, fraud detection, and industrial monitoring. Dr. Pang has published extensively in top-tier journals and conferences, contributing influential work that bridges theoretical advances and practical applications in data science.

Andrea Ceccarelli

University of Florence

Andrea Ceccarelli is Associate Professor in Computer Science at the Department of Mathematics and Informatics of the University of Florence (Italy), and has nowadays above 15 years of experience in the design and assessment of dependable and secure systems and System-of-Systems, with a preference for experimental approaches. He has published above 100 papers and he has been program co-chair of SRDS, SafeComp, LADC, and he is a member of the IFIP WG 10.4 on Dependable Computing and Fault Tolerance.

Daksha Yadav

Amazon

Dr. Yadav is a passionate Applied Scientist with expertise in leveraging large-scale data and machine learning to drive impactful business solutions. Currently, she utilizes her skills at Amazon to extract meaningful insights from real-time financial data using cutting-edge techniques including LLMs and Deep Learning. She has also delved into innovative approaches for detecting anomalies in time-series data using generative and transformer models. Holding a Ph.D. in Computer Science from West Virginia University, Dr. Yadav has a proven track record of research and development. Her contributions include multiple publications and patents in the fields of biometrics, machine learning, and computer vision.

Narges Armanfard (Chair)

Associate Professor

Narges Armanfard is an Associate Professor of Electrical and Computer Engineering at McGill University and Mila - Quebec AI Institute. She is also affiliated with McGill Centre for Intelligent Machines (CIM), McGill initiative in Computational Medicine (MiCM) and McGill Institute for Aerospace Engineering (MIAE). Dr. Armanfard is the founder and principal investigator of the iSMART Lab with the mission to pioneer advanced algorithms in artificial intelligence, with expertise in computer vision, time series analysis, tabular data, large language models, and visual language models.

Hadi Hojjati

AI Researcher (PhD)

Hadi received his Bachelor’s degree in Electrical Engineering from Sharif University of Technology, Iran. He started as an MSc student at the iSMART Lab. and fast-tracked to PhD. He has received Graduate Excellence Fellowship Award (GEF), McGill Engineering Doctoral Award (MEDA), GREAT Award, and AGE-WELL Award. He is currently doing research on multi-modal and multi-variate anomaly detection in time-series data.

Thi Kieu Khanh Ho

AI Researcher (PhD)

Khanh received her Master’s degree at Gwangju Institute of Science and Technology (GIST), South Korea. She was a researcher at Seoul National University Hospital (SNUH), South Korea, before moving to Montreal for her PhD. She has received the prestigious McGill Engineering Doctoral Award (MEDA), GREAT Award and is nominated for the prestigious Vanier Scholarship. Her research focuses on time-series data anomaly detection using generative models and graphs.

Thomas Lai

AI Researcher (PhD)

Thomas received his Bachelor of Engineering (B.Eng.) from McGill University. A year after starting his Master’s at the iSMART Lab, Thomas fast-tracked into a PhD. He is a recipient of the MEUSMA and FRQ awards. His research is on open-set anomaly detection.

Alexander Koran

AI Researcher (MSc)

Alex grew up near Boston, and he moved to Montreal after finishing high school to pursue his undergraduate studies at McGill. He completed his Bachelor’s Degree in Computer Engineering with a math minor and an AI minor in Fall 2023. Some of his research interests are algorithm design, machine learning applications, and quantum computing. He is now pursuing a Master’s of Science at the iSMART lab and is a recipient of the GEF award. His MSc thesis focuses on time series anomaly detection.

Jack Wei

AI Researcher (MSc)

Jack (Yi) Wei received his Bachelor’s degree in Computer Engineering with a minor in Mathematics from McGill University. He is the recipient of the McGill Engineering Undergraduate Student Award (MEUSMA). His interest lies in tabular data analysis.

Zihan Wang

AI Researcher (MSc)

Zihan received his Bachelor’s degree in Electrical and Computer Engineering from the University of Alberta, Canada. He is now an MSc student at the iSMART Lab. He is the recipient of the Graduate Excellence Fellowship Award. His research at the iSMART Lab is focused on continual learning with large language models for anomaly detection.