Institute for Infocomm Research (I²R)
Algorithms give computers stereoscopic vision
25 Sep 2023A computational breakthrough allows computers to better identify three dimensional objects by recognising relevant image features.
Pixel perfect with image-sharpening algorithms
28 Aug 2023Researchers develop a new image-processing algorithm that sharpens hazy images by distinguishing true colours and removing visual noise.
Traffic prediction framework gets the green light
16 Aug 2023A new machine learning platform offers more accurate traffic predictions for safer, less congested roads.
Teaching computers to tug heartstrings
4 Aug 2023A new automated video summarisation model uses viewers’ brain signals to extract reel highlights that evoke emotions.
Machine learning models graduate to the real world
5 Jun 2023A new framework gives pre-trained machine learning models the ability to perform optimally in real-world settings, even with limited training data.
Algorithms focus on hazy images
22 May 2023A new image dehazing algorithm sharpens both real-world and computer-generated images with unprecedented speed and accuracy.
Lessons in fault finding
28 Mar 2023Technology for finding non-visual defects in semiconductors leaps forward thanks to an online machine learning algorithm that learns on the fly.
Artificial intelligence that knows how you feel
14 Mar 2023Researchers build a state-of-the-art computational model that can identify emotional cues in real-life conversations
Keeping secrets in the cloud
22 Feb 2023A new cloud-based machine learning framework processes sensitive encrypted data 20 times faster than its predecessors.
How to get around in a jiffy
19 Jan 2023Researchers have built a navigation algorithm that leverages multidimensional real-world data to map faster and more efficient traffic routes.
On target for the precision health era
30 Dec 2022Multidisciplinary efforts across A*STAR are paving the way toward Singapore’s precision medicine vision.
Ghost-buster algorithm keeps watch
28 Nov 2022Computer scientists develop an algorithm that tracks moving objects faster and more accurately than current platforms.