Structured Prediction Models in Computer Vision | Efficient Convex Relaxation of Mixture Regression

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=yUMHAVkwx8o


Duration: 1:06:23
217 views
2

TALK 1 - Structured Prediction Models in Computer Vision Abstract: I'll present a summary of our recent work on using modern machine learning methods to solve computer vision problems. This essentially consists of using structured prediction models like max-margin structured estimators and conditional random fields. The computer vision problems we will discuss include graph matching, shape classification and object categorization. TALK 2 - Efficient Convex Relaxation of Mixture Regression with Application to Motion Segmentation Abstract: We give a semidefinite relaxation for maximum a posteriori estimation of a mixture of regression models. In addition we show how the semidefinite program can be exactly solved by a fast spectral method. We compare the proposed technique against Expectation-Maximization for synthetic problems as well as for problems of motion segmentation in computer vision, with promising results.



Other Videos By Microsoft Research


2016-09-07File Systems are Broken
2016-09-07Rebuilding Rome in a Day
2016-09-07Automatic Facial Expression Analysis
2016-09-07Public Symposium - Talk 1:Progress on Development of a Microfluidic Robot Scientist
2016-09-07UPCRC Multicore Applications Workshop - Welcome, and Visual Computing - Session # 1
2016-09-07And Then There's This: How Stories Live and Die in Viral Culture
2016-09-07Shaplets, Motifs and Discords: A set of Primitives for Mining Massive Time Series and Image Archives
2016-09-07Modern Computer Arithmetic [1/6]
2016-09-07ISP-Enabled Behavioral Ad Targeting without User Consent (and Beyond)
2016-09-07A Research Program Proposal--Universal Cache Miss Equations for the Memory Hierarchy
2016-09-07Structured Prediction Models in Computer Vision | Efficient Convex Relaxation of Mixture Regression
2016-09-07UPCRC Multicore Applications Workshop - Session # 6 - Human-machine Interaction
2016-09-07Inferring Rankings under Constrained Sensing
2016-09-07UPCRC Multicore Applications Workshop - Session # 5 - Human-machine Interaction
2016-09-07Audio Cameras for Audio-Visual Scene Analysis
2016-09-07Block Switching: Towards a Robust Protocol Stack for Diverse Wireless Networks
2016-09-07A Programming Language for the New Web
2016-09-07The Beauty and the Beast: Vulnerability in Red Hat's Packages
2016-09-07Debian: Anatomy of An Open Source Project
2016-09-07UPCRC Multicore Applications Workshop - Session # 3 - Social Interaction
2016-09-07Supersingular abelian varieties and modular forms


Tags:
microsoft research