Speaker: Dr. Ngan Le, University of Arkansas | Department of CSCE | Director of Artificial Intelligence and Computer Vision Lab
Date: Wednesday, November 29, 2023, 4:00 – 5:00 PM
Location: Science Engineering Hall (SCEN 408)
Title: Unbox the Black-box of Deep Learning in Computer Vision
Abstract: Image Understanding and Video Analysis stand as pivotal functions in the realm of Computer Vision. Instinctively, we, as humans, understand the content within images or videos through the intricate interplay of actors, pertinent objects, and their environmental context. However, despite remarkable strides in Computer Vision, a substantial portion of contemporary methods seems to sidestep this intrinsic principle of human perception, often designing the model of backbone networks to images or videos as an opaque, black-box process. In our upcoming talk, we aim to demystify this black-box approach, introducing models that are both explainable and interpretable. Our presentation will delve into the practical applications of explainable machine learning, specifically highlighting its role in video action understanding and medical imaging. By doing so, we hope to bridge the gap between traditional machine learning approaches and the intuitive ways in which humans understand visual content, fostering a deeper, more nuanced understanding of image and video analysis in Computer Vision.
Short Bio: Dr. Le holds the position of Assistant Professor and serves as the Director of the Artificial Intelligence & Computer Vision (AIVC) Lab within the Department of Electrical Engineering and Computer Engineering at the University of Arkansas, Fayetteville.Formerly a postdoc in Electrical and Computer Engineering at Carnegie Mellon University (CMU) during 2018-2019, Dr. Le completed her Ph.D. in ECE from CMU in 2018, along with an ECE Master’s (2015) from CMU, a CS Master’s from the University of Science, Vietnam (2009), and a CS Bachelor’s from the same university (2005).Her research covers a wide spectrum including Robotics, Artificial Intelligence (Machine Learning, Deep Learning, Reinforcement Learning), Computer Vision, Image and Video Understanding, Biomedical Imaging, and Vision-Language interfaces. Her work extends to applications like Multiple Object Tracking, 3D Object Reconstruction, Human Behavior Understanding, Animal Welfare, Video Summarization, Video Retrieval, and Action Recognition. She boasts 5 patents and is a co-author of 130+ papers spanning prestigious journals and conferences.Notably, she has taken on roles such as Associate Editor for Elsevier’s Machine Learning with Applications (MLWA) journal, Program Chair of Asilomar 2022, Technical Chair of MICAD 2022-2023, and has contributed as a Guest Editor to prominent publications including Artificial Intelligence for Biomedical Sensing, Analysis and Treatment 2021, as well as Robot and Machine Vision, Frontier 2020-2021.
Recent Comments