Visual Nearest Neighbor Search

Channel:
Microsoft Research
Subscribers:
351,000
Published on ● Video Link: https://www.youtube.com/watch?v=Al2pIZ4g8mw


Duration: 1:08:21
780 views
8

Template Matching finds the best match in an image to a given template and this is used in a variety of computer vision applications. I will discuss several extensions to Template Matching. First, dealing with the case where we have millions of templates that we must match at once, second dealing with the case of RGBD images, where depth information is available and finally, presenting a fast algorithm for template matching under 2D affine transformations with global approximation guarantees. Joint work with Simon Korman, Yaron Eshet, Eyal Ofek, Gilad Tsur and Daniel Reichman.



Other Videos By Microsoft Research


2016-06-21Statistical Text Analysis for Social Science
2016-06-21Mechanism Design and Economic Inference
2016-06-21Rethinking Machine Learning In The 21st Century: From Optimization To Equilibration
2016-06-21Making Machine Learning Reproducible with CodaLab
2016-06-21Using ConvNets, MALIS and crowd-sourcing to map the retinal connectome
2016-06-21Scalable Recognition of Human Activities for Pervasive Applications in Natural Environments
2016-06-21Program Synthesis for the Masses
2016-06-21Symmetry-Based Learning
2016-06-21Torch
2016-06-21Vowpal Wabbit
2016-06-21Visual Nearest Neighbor Search
2016-06-21Data Driven Student Feedback For MOOCs: Global Scale Education for the 21st century
2016-06-21Stan
2016-06-21Robust Probabilistic Inference
2016-06-21Deep Learning for Text Processing
2016-06-21Shogun
2016-06-213rd Pacific Northwest Regional NLP Workshop: Short Talks
2016-06-21Theory and Methods for Recovering Structured Patterns in High Dimensional Data
2016-06-21Sparse Stochastic Bandits
2016-06-21Representation, Modeling and Computation: Opportunities and Challenges of Modern Datasets
2016-06-21Keynote: ALMA, Chile, and the new challenges facing astronomy at the beginning of the 21st Century


Tags:
microsoft research
machine learning
deep neural networks