J.p. Lewis

Dr. J.p. Lewis


Research Focus & Metrics

Academic Career Length

43Years (1984-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2010 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
SBSimon Baker
Simon Baker
DSDaniel Scharstein
Daniel Scharstein
JLJ.p. Lewis
J.p. Lewis
SRStefan Roth
Stefan Roth
MBMichael J. Black
Michael J. Black
RSRichard Szeliski
Richard Szeliski
The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. The challenges for optical flow algorithms today go beyond the datasets and evaluation methods proposed in that paper. Instead, they center on problems associated with complex natural scenes, including nonrigid motion, real sensor noise, and motion discontinuities. We propose a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: (1) sequences with nonrigid motion where the ground-truth flow is determined by tracking hidden fluorescent texture, (2) realistic synthetic sequences, (3) high frame-rate video used to study interpolation error, and (4) modified stereo sequences of static scenes. In addition to the average angular error used by Barron et al., we compute the absolute flow endpoint error, measures for frame interpolation error, improved statistics, and results at motion discontinuities and in textureless regions. In October 2007, we published the performance of several well-known methods on a preliminary version of our data to establish the current state of the art. We also made the data freely available on the web at http://vision.middlebury.edu/flow/. Subsequently a number of researchers have uploaded their results to our website and published papers using the data. A significant improvement in performance has already been achieved. In this paper we analyze the results obtained to date and draw a large number of conclusions from them.

1 January 2007
Verified
Conference Paper
Closed access
SBSimon Baker
Simon Baker
SRStefan Roth
Stefan Roth
DSDaniel Scharstein
Daniel Scharstein
MBMichael J. Black
Michael J. Black
JLJ.p. Lewis
J.p. Lewis
RSRichard Szeliski
Richard Szeliski
The quantitative evaluation of optical flow algorithms by Barron et al. led to significant advances in the performance of optical flow methods. The challenges for optical flow today go beyond the datasets and evaluation methods proposed in that paper and center on problems associated with nonrigid motion, real sensor noise, complex natural scenes, and motion discontinuities. Our goal is to establish a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: sequences with nonrigid motion where the ground-truth flow is determined by tracking hidden fluorescent texture; realistic synthetic sequences; high frame-rate video used to study interpolation error; and modified stereo sequences of static scenes. In addition to the average angular error used in Barron et al., we compute the absolute flow endpoint error, measures for frame interpolation error, improved statistics, and flow accuracy at motion boundaries and in textureless regions. We evaluate the performance of several well-known methods on this data to establish the current state of the art. Our database is freely available on the Web together with scripts for scoring and publication of the results at http://vision.middlebury.edu/flow/.

4 October 2010 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
ALA. Lagae
A. Lagae
SLS. Lefebvre
S. Lefebvre
RCR. Cook
R. Cook
TDT. DeRose
T. DeRose
GDG. Drettakis
G. Drettakis
MZM. Zwicker
M. Zwicker

1 June 2009 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
MSMike Sips
Mike Sips
BNBoris Neubert
Boris Neubert
JLJ.p. Lewis
J.p. Lewis
PHPat Hanrahan
Pat Hanrahan

1 January 2008
Verified
Book Chapter
Closed access
PDF file
DSDeqing Sun
Deqing Sun
SRStefan Roth
Stefan Roth
JLJ.p. Lewis
J.p. Lewis
MBMichael J. Black
Michael J. Black

3 April 2020 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
WMWan-Duo Kurt Ma
Wan-Duo Kurt Ma
JLJ.p. Lewis
J.p. Lewis
WKW. Bastiaan Kleijn
W. Bastiaan Kleijn
We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks. The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates exploding and vanishing gradients, resulting in the ability to learn very deep networks without skip connections. There is no requirement for symmetric feedback or update locking. We find that the HSIC bottleneck provides performance on MNIST/FashionMNIST/CIFAR10 classification comparable to backpropagation with a cross-entropy target, even when the system is not encouraged to make the output resemble the classification labels. Appending a single layer trained with SGD (without backpropagation) to reformat the information further improves performance.