Computer vision

A new attribute-based approach to object detection helps visual artificial intelligence models spot unknown objects more accurately and efficiently.

A consistent rulebook of prompts could be the key to advancing artificial intelligence models, enhancing their image classification performance even when dealing with unknown objects.

A computational breakthrough allows computers to better identify three dimensional objects by recognising relevant image features.

A new diagnostic innovation powered by artificial intelligence could empower surgeons to make more accurate and effective clinical decisions for colon cancer patients.

Computer scientists develop an algorithm that tracks moving objects faster and more accurately than current platforms.

A new neural network designed by A*STAR researchers can train algorithms to visually detect defective products in production lines with limited data.

By linking past observations with future possibilities, a novel framework could help computers predict human actions more accurately.

A new deep learning method increases the accuracy and range of applications for computer vision platforms.

A*STAR scientists have devised a learning framework to enable machines to integrate visual, auditory and text data.

High dynamic range imaging combined with deep learning approaches could improve the ability of autonomous vehicles to recognize traffic lights.

Using deep-learning techniques to locate potential human activities in videos

Technology for fast and efficient detection of hand poses could lead to enhanced human-computer interactions