Download the Free Prime PubMed App to your smartphone or tablet.

Available for iPhone or iPad:

Unbound PubMed app for iOS iPhone iPadAlso Available:
Unbound MEDLINE
Unbound PubMed app for Android

Available for Mac and Windows Desktops and laptops:

Unbound PubMed app for WindowsUnbound PubMed app for MAC OS Yosemite Macbook Air pro
(distill)
481 results
  • Distant supervision for treatment relation extraction by leveraging MeSH subheadings. [Journal Article]
    Artif Intell Med 2019; 98:18-26Tran T, Kavuluru R
  • The growing body of knowledge in biomedicine is too vast for human consumption. Hence there is a need for automated systems able to navigate and distill the emerging wealth of information. One fundamental task to that end is relation extraction, whereby linguistic expressions of semantic relationships between biomedical entities are recognized and extracted. In this study, we propose a novel dist…
  • Progressive Object Transfer Detection. [Journal Article]
    IEEE Trans Image Process 2019Chen H, Wang Y, … Qiao Y
  • Recent development of object detection mainly depends on deep learning with large-scale benchmarks. However, collecting such fully-annotated data is often difficult or expensive for real-world applications, which restricts the power of deep neural networks in practice. Alternatively, humans can detect new objects with little annotation burden, since humans often use the prior knowledge to identif…
  • Building a Weakly Outgassing Comet from a Generalized Ohm's Law. [Journal Article]
    Phys Rev Lett 2019; 123(5):055101Deca J, Henri P, … Horányi M
  • When a weakly outgassing comet is sufficiently close to the Sun, the formation of an ionized coma results in solar wind mass loading and magnetic field draping around its nucleus. Using a 3D fully kinetic approach, we distill the components of a generalized Ohm's law and the effective electron equation of state directly from the self-consistently simulated electron dynamics and identify the drivi…
  • Enduring Cognitive and Linguistic Deficits in Individuals With a History of Concussion. [Journal Article]
    Am J Speech Lang Pathol 2019; :1-17Stockbridge MD, Newman R
  • Purpose The purpose of this research is to determine whether individuals with a history of concussion retain enduring differences in narrative writing tasks, which necessitate rapid and complex integration of both cognitive and linguistic faculties. Method Participants aged 12-40 years old, who did or did not have a remote history of concussion, were recruited to take an online survey that includ…
  • Orbital Vasculitides-Differential Diagnosis. [Review]
    Curr Rheumatol Rep 2019; 21(10):54Espinoza GM, Liu JL
  • The orbit is subject to a variety of vascular insults that manifest with both specific and nonspecific patterns of vision compromise. The aim of the following review is to highlight the ophthalmic clinical features of systemic vasculitides that most frequently involve the orbit and differentiate them from the most common non-vasculitic orbital disorders.
  • SUMMIT: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations. [Journal Article]
    IEEE Trans Vis Comput Graph 2019Hohman F, Park H, … Chau DH
  • Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often focuses on explaining predictions for single images or neurons. As predictions are often computed from millions of weights that are optimized over millions of ima…
  • Learning with privileged information via adversarial discriminative modality distillation. [Journal Article]
    IEEE Trans Pattern Anal Mach Intell 2019Garcia NC, Morerio P, Murino V
  • Heterogeneous data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while training data can be accurately collected to include a variety of sensory modalities, it is often the case that not all of them are available in real life (testing) scenarios, where a model has to be deployed. This raises the challenge of…
New Search Next