A new machine learning algorithm can predict the in-game actions of volleyball players with 80% accuracy.
A new computer model captures the human visual system's ability to quickly generate a detailed scene description from an image.
Study calls into question the use of current machine learning technologies in the search for extra-terrestrial intelligent life.
Researchers have identified neurons in the brains of praying mantises that are able to compute 3D direction and distance. The findings may help to develop better technology for machine and robotic vision.
Researchers have developed a new algorithm that enables robots to identify objects hidden in 3D data. The new system may help with improving robotic vehicles and autonomous robots.
BOLD5000, a new, large scale data set of brain scans of people viewing images, is helping researchers to better understand how the brain processes images. The data set is a big step towards using computer visual models to study biological vision.
Researchers report humans often miss objects in plain sight, especially if the size is inconsistent with the rest of the scene.
Researchers report AI could learn to recognize objects in from just a few examples and may better model human cognition.
Researchers have created an AI system that can solve SAT geometry questions as well as the average 11th grade student.
Researchers have developed a new method to evaluate how well computers can identify the relationships between objects.
The Never Ending Image Learner (NEIL) computer program is able to label images and learn associations with little human intervention.