学术报告

       Deep learning has become a major breakthrough in artificial intelligence and achieved amazing success on solving grand challenges in many fields including computer vision, speech recognition, and natural language processing. Its success benefits from big training data and super parallel computational power emerging in recent years, as well as advanced model design and training strategies. In this talk, deep learning research in the computer vision group at the Chinese University of Hong Kong (CUHK) will be introduced. DeepID invented by the CUHK team was the first to achieve over 99% face verification accuracy on the most well known face recognition benchmark Labeled Faces in the Wild (LFW), surpassing human performance. They won the challenge of object detection from video in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2015. The will talk start with a historical overview and introduction of deep learning. Through concrete examples on face recognition, object detection, object tracking, and crowd scene understanding, I will explain how to effectively design the architectures of deep models and learn visual feature representations. The talk is accessible to non-experts on deep learning including undergraduates.