Z
Zongyi Liu
Researcher at Amazon.com
Publications - 41
Citations - 2206
Zongyi Liu is an academic researcher from Amazon.com. The author has contributed to research in topics: Computer science & Gait (human). The author has an hindex of 10, co-authored 32 publications receiving 2091 citations. Previous affiliations of Zongyi Liu include Microsoft & University of Florida.
Papers
More filters
Journal ArticleDOI
The humanID gait challenge problem: data sets, performance, and analysis
TL;DR: The humanlD gait challenge problem is introduced, to provide a means for measuring progress and characterizing the properties of gait recognition, and represents a radical departure from traditional computer vision research methodology.
Journal ArticleDOI
Improved gait recognition by gait dynamics normalization
Zongyi Liu,Sudeep Sarkar +1 more
TL;DR: It is shown that improved gait recognition can be achieved after normalization of dynamics and focusing on the shape information, and improves performance on the UMD gait data set that exercises time variations for 55 subjects.
Proceedings ArticleDOI
Simplest representation yet for gait recognition: averaged silhouette
Zongyi Liu,Sudeep Sarkar +1 more
TL;DR: A robust representation for gait recognition that is compact, easy to construct, and affords efficient matching is presented that is comparable to the gait baseline algorithm, which is becoming the comparison standard in gait Recognition.
Journal ArticleDOI
Effect of silhouette quality on hard problems in gait recognition
Zongyi Liu,Sudeep Sarkar +1 more
TL;DR: A novel model based silhouette reconstruction strategy, based on a population based hidden Markov model (HMM), coupled with an eigen-stance model, to correct for common errors in silhouette detection arising from shadows and background subtraction.
Journal ArticleDOI
Outdoor recognition at a distance by fusing gait and face
Zongyi Liu,Sudeep Sarkar +1 more
TL;DR: The combination of outdoor gait and one outdoor face per person is superior to using two outdoor face probes per person or using two gait probes per people, which can considered to be statistical controls for showing improvement by biometric fusion.