Smarter, smaller AI models outperform bigger rivals at spotting mussel rafts from space
A comparative study of oriented YOLO detectors on very high-resolution satellite imagery shows that compact YOLO11 models outperform larger rivals ...
A comparative study of oriented YOLO detectors on very high-resolution satellite imagery shows that compact YOLO11 models outperform larger rivals ...
A new robotic system combines deep learning recognition with optimised grasp planning to harvest tomatoes in dense clusters with minimal ...
By feeding neural networks only optical flow and motion history images instead of raw video, researchers at TU Delft achieved ...
Researchers developed lightweight neural networks and a new RGB-D dataset that let robots detect accurate grasps for fruits of varying ...
A new asymmetric AI fusion framework that treats dermoscopic images as the primary representation and clinical photos as a corrective ...
A dual-track deep learning network combining Swin Transformer global context with convolutional feature pyramids classifies pear leaf diseases with 92.69% ...
Researchers have developed a wavelet-transform-based pedestrian detection model that improves accuracy on crowded benchmarks while cutting parameters by nearly 40 ...
A new two-stage statistical algorithm detects impulse noise through Beta distribution fitting, higher-order moments, and robust MAD estimation, then reconstructs ...
Researchers have built a deep learning framework that detects Treacher Collins syndrome from facial images on an NVIDIA Jetson Orin ...
A new review argues that AI-IoT dairy welfare systems must be designed as complete cyber–physical architectures, with digital twins still ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine