[Legacy Report] 3D Scene Image Cognition and Multi-modal Learning

#deep #learning
Share

 Abstract:  Deep Learning is still difficult to understand the spatial structure and semantics of object in complex environment. Her lab is interested in knowledge based object detection, which includes salient object detection, semantic parts model, multi-modal and multi-view learning, and so on. Her researches have been used in autonomous driving in heavy occlusion city scenes. 


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar
  • Canberra, Australian Capital Territory
  • Australia
  • Contact Event Host

  Speakers

Tsinghua University

Topic:

3D Scene Image Cognition and Multi-modal Learning

Biography:

Address:China