no code implementations • 20 Dec 2022 • Evgenya Pergament, Pulkit Tandon, Oren Rippel, Lubomir Bourdev, Alexander G. Anderson, Bruno Olshausen, Tsachy Weissman, Sachin Katti, Kedar Tatwawadi
The contributions of this work are threefold: (1) we introduce a web-tool which allows scalable collection of fine-grained perceptual importance, by having users interactively paint spatio-temporal maps over encoded videos; (2) we use this tool to collect a dataset with 178 videos with a total of 14443 frames of human annotated spatio-temporal importance maps over the videos; and (3) we use our curated dataset to train a lightweight machine learning model which can predict these spatio-temporal importance regions.
1 code implementation • 8 May 2022 • Evgenya Pergament, Pulkit Tandon, Kedar Tatwawadi, Oren Rippel, Lubomir Bourdev, Bruno Olshausen, Tsachy Weissman, Sachin Katti, Alexander G. Anderson
We use this tool to collect data in-the-wild (10 videos, 17 users) and utilize the obtained importance maps in the context of x264 coding to demonstrate that the tool can indeed be used to generate videos which, at the same bitrate, look perceptually better through a subjective study - and are 1. 9 times more likely to be preferred by viewers.
no code implementations • ICCV 2021 • Oren Rippel, Alexander G. Anderson, Kedar Tatwawadi, Sanjay Nair, Craig Lytle, Lubomir Bourdev
In this setting, for natural videos our approach compares favorably across the entire R-D curve under metrics PSNR, MS-SSIM and VMAF against all mainstream video standards (H. 264, H. 265, AV1) and all ML codecs.
no code implementations • ICCV 2019 • Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander G. Anderson, Lubomir Bourdev
We present a new algorithm for video coding, learned end-to-end for the low-latency mode.
no code implementations • ICML 2017 • Oren Rippel, Lubomir Bourdev
We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time.
2 code implementations • 18 Nov 2015 • Oren Rippel, Manohar Paluri, Piotr Dollar, Lubomir Bourdev
Beyond classification, we further validate the saliency of the learnt representations via their attribute concentration and hierarchy recovery properties, achieving 10-25% relative gains on the softmax classifier and 25-50% on triplet loss in these tasks.
no code implementations • NeurIPS 2015 • Oren Rippel, Jasper Snoek, Ryan P. Adams
In this work, we demonstrate that, beyond its advantages for efficient computation, the spectral domain also provides a powerful representation in which to model and train convolutional neural networks (CNNs).
Ranked #169 on Image Classification on CIFAR-100
4 code implementations • 19 Feb 2015 • Jasper Snoek, Oren Rippel, Kevin Swersky, Ryan Kiros, Nadathur Satish, Narayanan Sundaram, Md. Mostofa Ali Patwary, Prabhat, Ryan P. Adams
Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations.
Ranked #156 on Image Classification on CIFAR-10
2 code implementations • 24 Feb 2014 • David Duvenaud, Oren Rippel, Ryan P. Adams, Zoubin Ghahramani
Choosing appropriate architectures and regularization strategies for deep networks is crucial to good predictive performance.
1 code implementation • 5 Feb 2014 • Oren Rippel, Michael A. Gelbart, Ryan P. Adams
To learn these representations we introduce nested dropout, a procedure for stochastically removing coherent nested sets of hidden units in a neural network.