Zobrazeno 1 - 10
of 1 749
pro vyhledávání: '"Taylor, Jonathan"'
Autor:
Hu, Yueyu, Guleryuz, Onur G., Chou, Philip A., Tang, Danhang, Taylor, Jonathan, Maxham, Rus, Wang, Yao
Stereoscopic video conferencing is still challenging due to the need to compress stereo RGB-D video in real-time. Though hardware implementations of standard video codecs such as H.264 / AVC and HEVC are widely available, they are not designed for st
Externí odkaz:
http://arxiv.org/abs/2404.09979
Autor:
Guleryuz, Onur G., Chou, Philip A., Isik, Berivan, Hoppe, Hugues, Tang, Danhang, Du, Ruofei, Taylor, Jonathan, Davidson, Philip, Fanello, Sean
We propose sandwiching standard image and video codecs between pre- and post-processing neural networks. The networks are jointly trained through a differentiable codec proxy to minimize a given rate-distortion loss. This sandwich architecture not on
Externí odkaz:
http://arxiv.org/abs/2402.05887
Autor:
Craig, Erin, Pilanci, Mert, Menestrel, Thomas Le, Narasimhan, Balasubramanian, Rivas, Manuel, Gullaksen, Stein-Erik, Dehghannasiri, Roozbeh, Salzman, Julia, Taylor, Jonathan, Tibshirani, Robert
Pretraining is a popular and powerful paradigm in machine learning to pass information from one model to another. As an example, suppose one has a modest-sized dataset of images of cats and dogs, and plans to fit a deep neural network to classify the
Externí odkaz:
http://arxiv.org/abs/2401.12911
Autor:
Shimada, Soshi, Mueller, Franziska, Bednarik, Jan, Doosti, Bardia, Bickel, Bernd, Tang, Danhang, Golyanik, Vladislav, Taylor, Jonathan, Theobalt, Christian, Beeler, Thabo
The physical properties of an object, such as mass, significantly affect how we manipulate it with our hands. Surprisingly, this aspect has so far been neglected in prior work on 3D motion synthesis. To improve the naturalness of the synthesized 3D h
Externí odkaz:
http://arxiv.org/abs/2312.14929
Autor:
Fry, Kevin, Taylor, Jonathan E.
Many modern datasets, such as those in ecology and geology, are composed of samples with spatial structure and dependence. With such data violating the usual independent and identically distributed (IID) assumption in machine learning and classical s
Externí odkaz:
http://arxiv.org/abs/2310.10740
Autor:
Taylor, Jonathan
We define a class of morphisms between \'etale groupoids and show that there is a functor from the category with these morphisms to the category of $C^*$-algebras. We show that all homomorphisms between Cartan pairs of $C^*$-algebras that preserve th
Externí odkaz:
http://arxiv.org/abs/2310.03126
Inference for prediction errors is critical in time series forecasting pipelines. However, providing statistically meaningful uncertainty intervals for prediction errors remains relatively under-explored. Practitioners often resort to forward cross-v
Externí odkaz:
http://arxiv.org/abs/2309.07435