Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Reiter, Austin"'
We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging examples by re-adjusting their predicted class probability distribution u
Externí odkaz:
http://arxiv.org/abs/2109.13449
Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing. Here, we explore the use of unstructured external knowledge sources of image
Externí odkaz:
http://arxiv.org/abs/2104.08108
Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes. In this paper, we leverage such visual engagement clues as supervisory signals for representation learning. However, learning f
Externí odkaz:
http://arxiv.org/abs/2104.07767
An image is worth a thousand words, conveying information that goes beyond the physical visual content therein. In this paper, we study the intent behind social media images with an aim to analyze how visual information can help the recognition of hu
Externí odkaz:
http://arxiv.org/abs/2011.05558
Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby multiple featur
Externí odkaz:
http://arxiv.org/abs/2003.01607
Traditional action recognition models are constructed around the paradigm of 2D perspective imagery. Though sophisticated time-series models have pushed the field forward, much of the information is still not exploited by confining the domain to 2D.
Externí odkaz:
http://arxiv.org/abs/1911.08511
Autor:
Liu, Xingtong, Sinha, Ayushi, Ishii, Masaru, Hager, Gregory D., Reiter, Austin, Taylor, Russell H., Unberath, Mathias
We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires monocular endoscopic videos and a multi
Externí odkaz:
http://arxiv.org/abs/1902.07766
Robotic surgery has been proven to offer clear advantages during surgical procedures, however, one of the major limitations is obtaining haptic feedback. Since it is often challenging to devise a hardware solution with accurate force feedback, we pro
Externí odkaz:
http://arxiv.org/abs/1808.00057
Registering images from different modalities is an active area of research in computer aided medical interventions. Several registration algorithms have been developed, many of which achieve high accuracy. However, these results are dependent on many
Externí odkaz:
http://arxiv.org/abs/1806.10748
Autor:
Liu, Xingtong, Sinha, Ayushi, Unberath, Mathias, Ishii, Masaru, Hager, Gregory, Taylor, Russell H., Reiter, Austin
We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires sequential data from monocular endoscop
Externí odkaz:
http://arxiv.org/abs/1806.09521