Part-based Tracking with Cascaded Regression of Neighbours

Add to your list(s) Download to your calendar using vCal

• Xiaomeng Wang (University of Cambridge)
• Thursday 30 November 2017, 14:15-15:15
• SS03 Meeting Room, Computer Laboratory.

If you have a question about this talk, please contact Alexander Simpson.

This talk will start with an introduction of visual tracking and its challenging properties. It focuses on a part-based tracking method (TRIC-track) developed during my PhD. I will explain why the part-based method has advantages for modelling objects and how the ‘direct displacement prediction’ method can robustly estimate the target position. The implicit shape model and the ability of updating the shape model and appearance model jointly will also be presented.

This talk is part of the Rainbow Group Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• Rainbow Group Seminars
• SS03 Meeting Room, Computer Laboratory
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.