原田達也教授於計算機科學系特邀講座中分享特徵提取的見解

HKBU Department of Computer Science organised an insightful online distinguished lecture titled "Past, Present, and Future of Feature Extraction" on 7 March 2023 featuring Professor Tatsuya Harada from The University of Tokyo. His exceptional insights and expertise on the topic attracted researchers, students, and industry professionals interested in the rapidly evolving fields of computer vision and machine learning.

During the lecture, Professor Harada provided a comprehensive review of the evolution of feature extraction methods in deep learning, covering both the statistical feature extraction methods and the advent of deep learning. He also explored the limitations of traditional statistical feature extraction methods and their relevance to state-of-the-art neural network architectures.

The lecture sparked an engaging and thought-provoking discussion among the audience, who eagerly explored the future direction of feature extraction for constructing deep neural networks. Many insightful questions, particularly regarding the potential applications of advanced feature extraction techniques in various domains, were widely discussed.

For the full video of the distinguished lecture, please click here for details.

Professor Tatsuya Harada delivered an online Distinguished Lecture on “Past, Present, and Future of Feature Extraction” organised by the Department of Computer Science.

Professor Tatsuya Harada presented Discriminative Spatial Pyramid with examples of weights on Caltech101 dataset.

About the speaker
Professor Harada is a renowned scholar at the Research Center for Advanced Science and Technology at The University of Tokyo. He also serves as a team leader at RIKEN AIP and as the Vice Director of the Research Center for Medical Bigdata at the National Institute of Informatics, Japan. His research focuses on visual recognition, machine learning, and intelligent robots.