Organizer
 Zhengming Ding Northeastern University, USA |
 Ming Shao University of Massachusetts Dartmouth |
 Yun Fu Northeastern University, USA |
Overview
Multi-view data are extensively accessible nowadays thanks to various types of features, view-points and different sensors. For example, the most popular commercial depth sensor Kinect uses both visible light and near infrared sensors for depth estimation; automatic driving uses both visual and radar sensors to produce real-time 3D information on the road; and face analysis algorithms prefer face images from different views for high-fidelity reconstruction and recognition. All of them tend to facilitate better data representation in different application scenarios. Essentially, multiple features attempt to uncover various knowledge within each view to alleviate the final tasks, since each view would preserve both shared and private information. Recently there are a bunch of approaches proposed to deal with the multi-view visual data. Our tutorial covers most multi-view visual data representation approaches, centered around several major applications, i.e., multi-view clustering, multi-view classification, and zero-shot learning. It discusses the current and upcoming challenges. This would benefit the computer vision community in both industry and academia from literature review to future directions.Program
| Time | Content | Presenter |
|---|---|---|
| 8:30-9:00 | Opening | Zhengming Ding & Ming Shao |
| 9:00-10:30 | Multi-view Learning [Sample-Wise Correspondance] [Multi-view Clustering, Classification, Zero-Shot Learning] | Ming Shao |
| 10:30-11:00 | Coffee Break | |
| 11:00-12:30 | Transfer Learning [Class-Wise Correspondance] [Domain Aadaptation, Domain Generalization] | Zhengming Ding |