In a task measuring haptic object recognition ability, participants touch pairs of 3D-printed objects without looking at them and decide if they are exactly the same.

VoCap achieves precise localization and semantic understanding of objects in videos by processing video content alongside simple prompts (such as text ... marks a significant advancement in video ...

This capability is achieved through image processing and object recognition, which empower robots to perform tasks such as navigation, obstacle avoidance, and even interaction with humans. Debian, ...

Ayzenberg and researchers from Emory University compared the visual perceptual abilities of preschoolers and state-of-the-art AI models and found that these children outperformed the best computer ...