J
Jianbo Yang
Researcher at Duke University
Publications - 33
Citations - 2470
Jianbo Yang is an academic researcher from Duke University. The author has contributed to research in topics: Feature (computer vision) & Mixture model. The author has an hindex of 17, co-authored 30 publications receiving 2057 citations. Previous affiliations of Jianbo Yang include Institute for Infocomm Research Singapore & Durham University.
Papers
More filters
Proceedings Article
Deep convolutional neural networks on multichannel time series for human activity recognition
TL;DR: This method adopts a deep convolutional neural networks (CNN) to automate feature learning from the raw inputs in a systematic way and makes it outperform other HAR algorithms, as verified in the experiments on the Opportunity Activity Recognition Challenge and other benchmark datasets.
Journal ArticleDOI
Coded aperture compressive temporal imaging
Patrick Llull,Xuejun Liao,Xin Yuan,Jianbo Yang,David S. Kittle,Lawrence Carin,Guillermo Sapiro,David J. Brady +7 more
TL;DR: This work uses mechanical translation of a coded aperture for code division multiple access compression of video to discuss the compressed video's temporal resolution and present experimental results for reconstructions of > 10 frames of temporal data per coded snapshot.
Journal ArticleDOI
Video compressive sensing using Gaussian mixture models.
Jianbo Yang,Xin Yuan,Xuejun Liao,Patrick Llull,David J. Brady,Guillermo Sapiro,Lawrence Carin +6 more
TL;DR: The efficacy of the proposed Gaussian mixture model (GMM)-based inversion method is demonstrated with videos reconstructed from simulated compressive video measurements, and from a realCompressive video camera.
Journal ArticleDOI
Compressive Sensing by Learning a Gaussian Mixture Model From Measurements
Jianbo Yang,Xuejun Liao,Xin Yuan,Patrick Llull,David J. Brady,Guillermo Sapiro,Lawrence Carin +6 more
TL;DR: This work derives a maximum marginal likelihood estimator (MMLE) that maximizes the likelihood of the GMM of the underlying signals given only their linear compressive measurements, and extends it to a GMM with dominantly low-rank covariance matrices, to gain computational speedup.
Proceedings ArticleDOI
Low-Cost Compressive Sensing for Color Video and Depth
Xin Yuan,Patrick Llull,Xuejun Liao,Jianbo Yang,David J. Brady,Guillermo Sapiro,Lawrence Carin +6 more
TL;DR: A simple and inexpensive modification is made to a conventional off-the-shelf color video camera, from which the recovered frames can be focused at a different depth, and fast recovery is achieved by an anytime algorithm exploiting the group-sparsity of wavelet/DCT coefficients.