Investigators developed and validated a masked autoencoder deep learning model using vision transformer technology to automate the detection and grading of nuclear cataracts from slit-lamp images.

BrainChip has introduced a new Radar Reference Platform designed to improve real‑time object identification at the edge, addressing what the company describes as a longstanding limitation in ...

XPANCEO, a deep-tech company developing smart contact lenses, has unveiled a passive eye-tracking system that achieves ...

A new study maps the rapidly evolving field of intelligent colonoscopy. It argues that the next leap will come not from isolated-task modeling alone ...

Abstract: Deploying deep learning models on UAV-based edge platforms for railway track foreign object detection is often limited by large model size and heavy computation. To address these issues, ...

The U.S. Navy recently decommissioned the minesweeping vessels that it had operating in the Persian Gulf region ...

Flexible ureteroscopy (FURS) has become a standard minimally invasive treatment for kidney stones. However, flexible ureteroscopy has advanced significantly; surgeons still rely on subjective visual ...

Object detection remains a fundamental yet challenging problem in machine vision. Over the past decade, numerous state-of-the-art solutions have been developed, predominantly based on deep learning.

Deep-sea organism detection is one of the key technologies in deep-sea resource research and conservation. However, challenges such as low recognition accuracy and insufficient robustness arise due to ...