上海科技大学 | English | 地图
首页> 新闻信息> 活动
Semantic-based Visual Content Creation for Digital Memories
Date:2018/10/17     Browse:691

Speaker:     Dr. Sing Bing Kang 

Time:          15:30—16:30, Oct 17

Location:    Room 1C-101, SIST Building

Host:          Prof. Jingyi Yu

Abstract:

The wide range of commercial and consumer imaging devices makes it easy for anyone to capture images and videos practically anywhere. Such devices include smartphones, sports or action cameras, and drones. Images and videos are visual records of scenes at selected moments in time; in many cases, they represent personal memories. Attaching semantics to images and videos allow the visual experience or virtual navigation to be more appealing and personalized. (By scene semantics, I mean identities of objects in the scene or high-level scene features.) In this talk, I demonstrate the benefits of semantic-based visual content creation using the examples of 360-degree or panoramic videos and cinemagraphs, which is a kind of looping video. I will also touch on Microsoft Pix, an “intelligent camera” app which was released on the iOS on July 27, 2016. Microsoft Pix is among TIME's top 50 apps and NYTimes' outstanding apps for 2016.


Bio: 

Sing Bing Kang received his Ph.D. degree in robotics from Carnegie Mellon University in 1994. He is Principal Researcher at Microsoft Corporation, and his research interests include computational photography and image-based modeling. He has published about 60 peer-reviewed journal papers and about 90 peer-reviewed conference papers. He has also coedited two books (“Panoramic Vision and Emerging Topics in Computer Vision”) and coauthored two books (“Image-Based Rendering and Image-Based Modeling of Plants and Trees”). On the community service front, he has served as Area Chair for the major computer vision conferences (CVPR, ICCV, ECCV) and as papers committee member for SIGGRAPH and SIGGRAPH Asia. Sing Bing was Program Chair for ACCV 2007 and CVPR 2009, and was Associate Editor-In-Chief for IEEE Transactions on Pattern Analysis and Machine Intelligence from 2010-2014. He is a fellow of the IEEE.

SIST-Seminar 18075