Results 71 to 80 of about 543,028 (283)
Deep Self-Taught Learning for Weakly Supervised Object Localization
, 2017 Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision.
Feng, Jiashi +4 more
core +1 more source
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective People with epilepsy (PWE) may experience cognitive deficits but fail to undergo formal evaluation. This study compares cognitive status between PWE and healthy controls in the West African Republic of Guinea. Methods A cross‐sectional, case–control study was conducted in sequential recruitment phases (July 2024–July 2025) at Ignace ...
Maya L. Mastick +14 more
wiley +1 more source
Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning
, 2018 Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help ...
Funkhouser, Thomas +5 more
core +1 more source
Remote Assessment of Ataxia Severity in SCA3 Across Multiple Centers and Time Points
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Spinocerebellar ataxia type 3 (SCA3) is a genetically defined ataxia. The Scale for Assessment and Rating of Ataxia (SARA) is a clinician‐reported outcome that measures ataxia severity at a single time point. In its standard application, SARA fails to capture short‐term fluctuations, limiting its sensitivity in trials.
Marcus Grobe‐Einsler +20 more
wiley +1 more source
Self-Supervised Relative Depth Learning for Urban Scene Understanding
, 2018 As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over time: as the agent
A Geiger +15 more
core +1 more source
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective To explore how cerebral hypoxia and Normal‐Appearing White Matter (NAWM) integrity affect MS lesion burden and clinical course. Methods Seventy‐nine MS patients, including 13 clinically isolated syndrome (CIS) patients and 66 relapsing–remitting multiple sclerosis (RRMS) patients, and 44 healthy controls (HCs) were recruited from ...
Xinli Wang +8 more
wiley +1 more source
EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras
, 2018 Event-based cameras have shown great promise in a variety of situations where frame based cameras suffer, such as high speed motions and high dynamic range scenes. However, developing algorithms for event measurements requires a new class of hand crafted
Chaney, Kenneth +3 more
core +1 more source
Elevated Connectivity During Language Processing Is Associated With Cognitive Performance in SeLECTS
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Self‐Limited Epilepsy with Centrotemporal Spikes (SeLECTS) is associated with language impairments despite seizures originating in the motor cortex, suggesting aberrant cross‐network interactions. Here we tested whether functional connectivity in SeLECTS during language tasks predicts language performance.
Wendy Qi +8 more
wiley +1 more source
BMC Medical ImagingSelf-supervised pretraining has been observed to be effective at improving feature representations for transfer learning, leveraging large amounts of unlabelled data.
Blake VanBerlo +2 more
doaj +1 more source
Improvements to context based self-supervised learning
, 2018 We develop a set of methods to improve on the results of self-supervised learning using context. We start with a baseline of patch based arrangement context learning and go from there.
Chen, Barry Y. +2 more
core +1 more source