On the afternoon of May 22, 2024, at 4:00 pm, Professor Han Jungong, an international visiting scholar from the University of Sheffield in the UK, was invited to give an academic presentation titled When Deep Learning Meetings Computer Vision: Challenges, Solutions and Trends at our institution.
Abstract: For around a decade now, deep learning has revolutionized computer vision research However, some key questions remain unanswered: 1 Why do deep learning networks require extreme high dimensions to encode representational information while human vision does not? 2. Can convolutional neural networks effectively report image/video data? 3. How can multimodal data fusion be achieved in deep networks? How can machines learn from a few annotated samples? In this talk, I will discuss our team's efforts to address these questions, highlighting progress and future directions at the intersection of deep learning and computer vision
Reported by: Han Jungong, Chair Professor of the School of Computer Science at the University of Sheffield (Red Brick University, 6 Nobel laureates), Head of the Computer Vision Team, and Honorary Professor at the University of Warwick in the United Kingdom. Han Jungong and his team have contributed multiple original works in research fields such as multimedia content analysis, multimodal visual perception, and machine learning. They have published over 100 IEEE/ACM Trans papers, 70 CCF A-class conference papers, and have been selected for the top 2% of global scientists by Stanford University for consecutive years. Google Scholar has cited more than 19200 times, with an H-index of 70. Serve as the executive editor in chief and deputy editor in chief of 5 well-known journals in this field (3 IEEE Transactions). Obtained 1 patent from the European Union and 1 patent from the United States each; Commercialization of three technologies; One of them won an international industrial award. Member of the International Pattern Recognition Association and the Asia Pacific Artificial Intelligence Association.
