Mission

Our mission is to create a series of tutorials that focus on exploring important AI technical directions. For each direction, we invite a world leading expert to present an AI tutorial. Each AI tutorial aims at: (1) providing a historic overview of the subject with key milestones by highlighting those methods that have shaped the direction of the subject up-to-date; (2) surveying the most relevant state-of-the-art methods; (3) presenting an outlook of the subject and an overview of future directions. Our speakers — all hands-on investigators in various areas of AI — will discuss methods and techniques by striking a suitable balance between technical details and intuitions.

*All talks will be recorded and shared online to enable a larger audience to access and enjoy the learning material.

Tutorials

Research Area Speaker Time Location Video
Human Action and Activity Recognition Greg Mori 2018-09-17 9:00a.m.-11:30a.m. 电院楼3-200报告厅,Shanghai Jiao Tong University Minhang Campus
Scene Understanding Jia Deng 2018-11-23 14:00p.m.-17:30p.m. 信息大楼多功能厅,Tsinghua University,Beijing,China
3D Reconstruction Yasutaka Furukawa 2018-12-12 14:00p.m.-17:30p.m. 英杰国际交流中心阳光厅,Peking University Beijing,China
Learning Visual Models with Minimal Human Supervision Vittorio Ferrari 2019-04 TBD
Joint Object Detection, Segmentation and Pose Estimation Inviting
Fine-grained Recognition Inviting
Multiple Object Tracking Inviting
Image and Video Compression Inviting
Video Segmentation Inviting
Vision & Language Inviting
Domain Adaptation Inviting
Generative Adversarial Networks Inviting
More to come

Information

Human Activity Recognition: Past Progress and Emerging Directions

  • Speaker

    Greg Mori

  • Time

    2018-09-17 9:00 a.m.-11:30 a.m.

  • Location

    电院楼3-200报告厅,Shanghai Jiao Tong University
    Minhang Campus, China

  • Video

Greg Mori received a Ph.D. in Computer Science from the University of California, Berkeley in 2004. He received an Hon. B.Sc. in Computer Science and Mathematics with High Distinction from the University of Toronto in 1999. He serves on the organizing committees of the major computer vision / machine learning conferences (CVPR, ECCV, ICCV, NIPS), and will be a Program Chair for CVPR 2020. He is currently a Professor in the School of Computing Science at Simon Fraser University and Research Director for Borealis AI Vancouver.

Teaching Computers to See and Think

  • Speaker

    Jia Deng

  • Time

    2018-11-23 14:00 p.m. - 17:30 p.m.

  • Location

    信息大楼多功能厅,Tsinghua University,Beijing,China

  • Slides

Jia Deng is an Assistant Professor of Computer Science at Princeton University. His research focus is on computer vision and machine learning. He received his Ph.D. from Princeton University and his B.Eng. from Tsinghua University, both in computer science. He is a recipient of the Sloan Research Fellowship, the PAMI Mark Everingham Prize, the Yahoo ACE Award, a Google Faculty Research Award, the ICCV Marr Prize, and the ECCV Best Paper Award.

3D Reconstruction: From Sensing, Perception, to Cognition

  • Speaker

    Yasutaka Furukawa

  • Time

    2018-12-12 14:00 p.m.-17:30 p.m.

  • Location

    英杰国际交流中心阳光厅, Peking University, Beijing,China

  • Video

Yasutaka Furukawa is an assistant professor of Computing Science at Simon Fraser University. Prior to SFU, He was an assistant professor at Washington University in St. Louis, and a software engineer at Google. He is a pioneer in automated 3D reconstruction and visualization. His multi-view stereo (MVS) algorithm has been recognized as the best 3D reconstruction algorithm from calibrated photographs, and has been used at numerous academic and industrial settings. He received the best student paper award at ECCV 2012, the best paper award at 3DV 2013, and the NSF CAREER Award in 2015. He completed his Ph.D. at Computer Science Department of University of Illinois at Urbana-Champaign in May 2008.