Title: Precognition: Seeing through the Future
Presenter(s): Khoa Luu
Date: January 26, 2022
Description
Vision-based detection and recognition studies have been recently achieving highly accurate performance and were able to bridge the gap between research and real-world applications. Beyond these well-explored detection and recognition capabilities of modern algorithms, vision-based forecasting will likely be one of the next big research topics in the field of computer vision and artificial intelligence. Vision-based prediction is one of the critical capabilities of humans, and potential success of automatic vision-based forecasting will empower and unlock human-like capabilities in machines and robots.
One important application is in autonomous driving technologies, where vision-based understanding of a traffic scene and prediction of movement of traffic actors is a critical piece of the autonomous puzzle. Various sensors such as camera and lidar are used as “eyes” of a vehicle, and advanced vision-based algorithms are required to allow safe and effective driving. Another area where vision-based prediction is used is medical domain, allowing deep understanding and prediction of future medical conditions of patients. Especially with the recent introduced Metaverse from Meta (or Facebook), a network of 3D virtual worlds focused on social connection, this topic has become more important. However, despite its potential and relevance for real-world applications, visual forecasting or precognition has not been in the focus of new theoretical studies and practical applications as much as detection and recognition problems.
In this presentation, we will discuss recent approaches and research trends not only in anticipating human behavior understanding from videos but also precognition in multiple other visual applications, such as: healthcare, human face aging prediction, autonomous drone forecasting and tracking, etc.
Presenter Bios
Dr. Khoa Luu is currently an Assistant Professor and the Director of Computer Vision and Image Understanding (CVIU) Lab in Department of Computer Science and Computer Engineering at University of Arkansas, Fayetteville. He is also serving as an Associate Editor of IEEE Access Journal.
He was the Research Project Director in Cylab Biometrics Center at Carnegie Mellon University (CMU). He has joined to develop several successful AI applications, including AI-based Smart Insect Monitoring System, Age-invariant Face Recognition, Mutli-camera Multi-Object Tracking, Long-range Biometrics and Soft Biometrics Systems, Perception and Prediction solutions for robots.
He is teaching Computer Vision, Image Processing, and Introduction to Artificial Intelligence courses in CSCE Department at University of Arkansas, Fayetteville. His research interests focus on various topics, including Biometrics, Object Tracking, Human Behavior Understanding, Scene Understanding, Domain Adaptation, Deep Generative Modeling, Compressed Sensing and Quantum Machine Learning. He has received four patents and two best paper awards and coauthored 120+ papers in conferences, technical reports, and journals. His Ph.D student won the Best Research Award in NSF DART 2021.
He is a co-organizer and a chair of CVPR Annual Precognition Workshop in 2019, 2020, 2021, 2022; MICCAI Workshop in 2019, 2020 and ICCV Workshop in 2021. He is a PC member of AAAI’20, AAAI’21, AAAI’22 ICPRAI’20, ICPRAI’22 and a Technical member of IJCAI-ECAI’22, ICPR’22. He is also a reviewer for numerous top-tier AI conferences and journals, such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, FG, BTAS, IEEE-TPAMI, IEEE-TIP, Journal of Pattern Recognition, Journal of Image and Vision Computing, Journal of Signal Processing, Journal of Intelligence Review, IEEE Access Trans., etc. He was a vice-chair of Montreal Chapter IEEE SMCS in Canada from September 2009 to March 2011.