复旦大学-浙江师范大学“机器学习与视觉前沿论坛”系列报告五

报告题目：Robust and Efficient Visual Representation Learning

报告专家：朱霖潮（悉尼科技大学）

报告时间：11月29日15:00-15:45

报告地点：腾讯会议号766-826-483（复旦浙师大MLV前沿论坛）

报告摘要：In this talk, I will introduce our recent works on large-scale visual scene understanding. First, I will explain the major challenges for large-scale visual analysis. I will introduce our robust image classification model and discuss the impact of noisy data in real-world application. Second, I will introduce an efficient video modeling method for egocentric videos. It effectively tackles video sequences and provides a feasible solution towards action understanding. Finally, I will discuss the methods to improve model efficiency when dealing with multi-modal data (such as audio, text), and demonstrate the potential multi-modal video applications in the real-world.

 邀请人:郑忠龙