Lectures Home > Lectures > Content

Multi-view Learning and Its Applications in Cross-modal Retrieval and Clustering

Release date : May 22, 2019 office viewed :

TitleMulti-view Learning and Its Applications in Cross-modal Retrieval and Clustering

Location:N3-332 

Time:8:30 am, 23rd May 2019 

Speaker:Jianlong Wu


Abstract: 

With the development of technology, we can collect mass of data of different views from the Internet, such as different kinds of modalities and features. It is very important to explore the correlation among different views to facilitate related applications, including the cross-modal retrieval and clustering. Deep learning methods can also be incorporated to further improve the performance. In this talk, I will introduce the recent process on multi-view learning based on my research achievements.


Biography: 

Jianlong Wu is a final year Ph.D. student in School of Electronics Engineering and Computer Science, Peking University, advised by Professor Zhouchen Lin and Professor Hongbin Zha. In 2014, he earned his B.E. degree from the advanced class of the department of electronics and information engineering, Huazhong University of Science and Technology. His research interests include deep learning, multi-view clustering, and cross-modal retrieval. He has published more than 10 articles in top journals and conferences, such as Trans. Image Processing, ICML, SIGIR, and ECCV.