主 講 人：謝凌曦博士

地　　點(diǎn)：祥聯(lián)廳

主 辦 方：物理與信息工程學(xué)院

開始時(shí)間：2018-05-05 15:00

謝凌曦博士簡(jiǎn)介：Lingxi Xie obtained his B.E and Ph.D. degree from Tsinghua University in 2010 and 2015, respectively. He is currently a post-doctoral researcher in the University of California, Los Angeles. From 2013 to 2015, he was a research intern at Microsoft Research Asia. He was a visiting researcher at the University of Texas as San Antonio in 2014. Lingxi has been working on computer vision and multimedia information retrieval, especially in the area of image classification, image retrieval and object detection. He is also interested in the theory and application of deep learning. Lingxi obtained the best paper award on ICMR 2015.

報(bào)告主要內(nèi)容簡(jiǎn)介：Deep neural networks have been widely applied to a wide range of computer vision tasks. In this talk, we will first take a brief review on the history and basic concepts of deep learning. Then, starting from the most fundamental problem, image recognition, we will introduce several efforts in increasing the ability of neural networks. Based on powerful models, we can either transfer knowledge to other image applications, or try to understand how these models capture visual concepts at different levels.