*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Allie McFadden
Communications Officer
allie.mcfadden@cc.gatech.edu
Summary Sentence: Huang is an assistant professor at The University of Texas at Austin. his recent focus is on developing machine learning algorithms (particularly deep learning) that leverage Big Data to solve core problems in computer vision, and computer graphics.
Full Summary: The Machine Learning Center at Georgia Tech presents a seminar by Qixing Huang of The University of Texas at Austin. The event will be held in the Marcus Nanotechnology Building, Rooms 1116-1118, from 12:15-1:15 p.m. and is open to the public.
Qixing HuangThe Machine Learning Center at Georgia Tech presents a seminar by Qixing Huang of The University of Texas at Austin. The event will be held in the Marcus Nanotechnology Building, Rooms 1116-1118, from 12:15-1:15 p.m. and is open to the public.
Talk Title
Map Synchronization: from Object Correspondences to Neural Networks
Abstract
Maps between geometric objects are deeply interesting. High-quality maps facilitate information propagation and aggregation, leading to numerous applications in geometry reconstruction, synthesis, analysis and prediction. In the deep learning era, the concept of maps naturally generalizes to neural networks between pairs of domains. Despite the importance of maps, map computation remains quite challenging, particularly between dissimilar objects. Map synchronization addresses this challenge by jointly optimizing maps among a collection of relevant objects, which allows us to compute maps between dissimilar objects by composing maps along paths of similar object pairs.
In this talk, we will discuss several recent works on map synchronization: joint map and symmetry synchronization, learning to transformation synchronization and learning a network of neural networks. We will focus on both theoretical connections to optimization, representation theory and graph theory, and practical applications in 3D reconstruction and 3D understanding.
Bio
Qixing Huang obtained his PhD in Computer Science from Stanford University in 2012. From 2012 to 2014 he was a postdoctoral research scholar at Stanford University. From 2014 to 2016 he was a research assistant professor at Toyota Technological Institue at Chicago. He received his MS and BS in Computer Science from Tsinghua University. He has also interned at Google Street View, Google Research and Adobe Research. His research spans computer vision, computer graphics, computational biology and machine learning. In particular, his recent focus is on developing machine learning algorithms (particularly deep learning) that leverage Big Data to solve core problems in computer vision, computer graphics and computational biology. He is also interested in statistical data analysis, compressive sensing, low-rank matrix recovery, and large-scale optimization, which provide theoretical foundation for much of his research.
RSVP here by Tuesday, November 27th
