New AI Learns to Track Surgical Robots in Real Time, Even When Blood and Smoke Block the View
Researchers at the University of Leeds have developed PICO, a single-stage AI system that estimates the full 3D position and ...
Researchers at the University of Leeds have developed PICO, a single-stage AI system that estimates the full 3D position and ...
Researchers in China have developed REF-VMUNetUp, a Mamba-based network with rotary position embeddings and dynamic upsampling that improves multi-organ segmentation ...
Researchers in Taiwan have combined drone-mounted cameras, the YOLOv8 detector and 5G transmission to identify cracked and detached building tiles ...
A new deep learning framework called DeepGATE reads analog gas meter dials from camera images in real time, improving measurement ...
A new stem-encoder-decoder neural network runs crowd counting at up to 381.7 frames per second on desktop GPUs and 71.9 ...
Researchers have developed a U-Net-based segmentation network that recovers high-frequency image details lost during downsampling, achieving record accuracy in segmenting ...
Researchers in Taiwan developed a low-cost Raspberry Pi camera system that tracks dam displacement and vibration to deliver early-warning signals ...
A new survey in Machine Learning provides an extensive taxonomy of attention mechanisms and more than thirty Transformer variants that ...
A new neural network called CDGaitFusion fuses shared motion patterns with individual-specific features to recognize people by their gait despite ...
Researchers have developed a real-time AI framework and a new field-captured dataset, VerBeet, that localize sugar beets and detect breakage ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine