Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the eventorganiser domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/rossbere/uccs.justdev.co/wp-includes/functions.php on line 6121
Kfir Aberman (Google) – Learning the Structure of Motion – Department of Computer Science
Date & Time:
October 4, 2021 10:00 am – 11:00 am
Location:
Crerar 298, 5730 S. Ellis Ave., Chicago, IL,
10/04/2021 10:00 AM 10/04/2021 11:00 AM America/Chicago Kfir Aberman (Google) – Learning the Structure of Motion Crerar 298, 5730 S. Ellis Ave., Chicago, IL,

Warning: Attempt to read property "term_id" on array in /home/rossbere/uccs.justdev.co/wp-content/themes/csuc/inc/classes/class-single-event.php on line 61

Warning: Attempt to read property "term_id" on array in /home/rossbere/uccs.justdev.co/wp-content/themes/csuc/inc/classes/class-single-event.php on line 61

Learning the Structure of Motion

Human motion is a fundamental attribute, underlying human actions, gestures, and behavior. It is inherently a 4D entity, commonly represented as a low-level encoding: a temporal sequence of poses, specified as a set of joint positions and/or angles. However, motion is a high-level, abstract, attribute that is concealed under this representation. For example, the same motion performed by two individuals with different skeletons might have significantly different low-level encoding. 

In this talk, we will present two learning frameworks that aim to learn the essence of motion and enables retargeting the motion of one performer to another. The first deals with the retargeting of video-captured motion between different human performers, without the need to explicitly reconstruct 3D poses and/or camera parameters, and the second is aiming at 3D motion retargeting between skeletons, which may have different structures and number of joints, yet derived from the same topology. 

The shared key idea in both frameworks is the disentanglement of a motion signal into fundamental, abstract, components that enables separating the dynamic aspects of motion from the static ones, using unique deep neural network structures. Our framework demonstrates state-of-the-art performances in both of the retargeting tasks, and can be further exploited for other motion analysis and synthesis tasks such as motion retrieval and motion style transfer.

Host: Rana Hanocka

Kfir Aberman

Research Scientist, Google Research

Kfir Aberman is a research scientist at Google Research in San Francisco. His research interests include deep neural network architectures for various computer graphics applications. In particular, his work is focused on analysis, synthesis, and manipulation of human motion in real videos as well as 3D character animation. Kfir received his Ph.D. from the Electrical Engineering department at Tel-Aviv University, under the supervision of Prof. Daniel Cohen-Or, and his M.Sc. (Cum Laude) and B.Sc. (Summa Cum Laude) from the Technion. He serves as a reviewer of various journals and conferences within the graphics community.

Related News & Events

UChicago CS News

Three UChicago PhD Students From The Department of Computer Science Named To Forbes 30 Under 30 List

Nov 28, 2023
UChicago CS News

High School Students In The Collegiate Scholars Program Get To Know Robots

Nov 14, 2023
UChicago CS News

AxLab Features Multidisciplinary Works at World’s Largest Art and Technology Festival

Nov 03, 2023
UChicago CS News

CS Alumni Spotlight: Former Student Andrew McNutt Talks Visualization Career, Lessons From UChicago, And The Road From PhD to Tenure Track at University of Utah

Oct 31, 2023
UChicago CS News

UChicago Undergrad Analyzes Machine Learning Models Used By CPD, Uncovers Lack of Transparency About Data Usage

Oct 31, 2023
UChicago CS News

UChicago CS Chair, Faculty, and Students Inducted Into Samsung Hall Of Fame For Identifying Vulnerability In SmartTVs

Oct 30, 2023
UChicago CS News

CS PhD Student J. Gregory Pauloski Named Recipient of 2023 ACM-IEEE CS George Michael Memorial HPC Fellowship

Oct 27, 2023
UChicago CS News

Research Suggests That Privacy and Security Protection Fell To The Wayside During Remote Learning

A qualitative research study conducted by faculty and students at the University of Chicago and University of Maryland revealed key...
Oct 18, 2023
UChicago CS News

Five UChicago CS students named to Siebel Scholars Class of 2024

Oct 02, 2023
UChicago CS News

UChicago Computer Scientists Design Small Backpack That Mimics Big Sensations

Sep 11, 2023
UChicago CS News

UChicago Researchers Win Internet Defense Prize and Distinguished Paper Awards at USENIX Security

Sep 05, 2023
UChicago CS News

Hank Hoffmann Named New Chair For The University of Chicago’s Department of Computer Science

Aug 28, 2023
arrow-down-largearrow-left-largearrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-smallbutton-arrowclosedocumentfacebookfacet-arrow-down-whitefacet-arrow-downPage 1CheckedCheckedicon-apple-t5backgroundLayer 1icon-google-t5icon-office365-t5icon-outlook-t5backgroundLayer 1icon-outlookcom-t5backgroundLayer 1icon-yahoo-t5backgroundLayer 1internal-yellowinternalintranetlinkedinlinkoutpauseplaypresentationsearch-bluesearchshareslider-arrow-nextslider-arrow-prevtwittervideoyoutube