Edge AI Eyewear Integrates Conversational Detection and Action Recognition
Researchers have engineered ExoAction, a unified edge-AI framework deployed on smart eyewear that simultaneously identifies conversational engagement and recognizes human ...
Researchers have engineered ExoAction, a unified edge-AI framework deployed on smart eyewear that simultaneously identifies conversational engagement and recognizes human ...
A modified YOLO11n neural network optimized with TensorRT achieved a 98.90 percent detection accuracy while cutting inference latency to 4.6 ...
The BCEA-YOLO framework improves underwater object detection by integrating multi-scale attention and adaptive feature fusion to effectively identify tiny, low-contrast ...
Researchers have introduced NVCR, an extensible C++20 native runtime that accelerates neural video compression execution while substantially reducing host memory ...
A lightweight YOLOv8-based detection model with three-branch attention and enhanced multi-scale fusion achieved 99.2 percent average precision on insulator defects ...
A benchmark study found that EDGI-YOLO improved mAP@0.5 by 3.94 percentage points over YOLOv8n on NEU-DET while reducing parameters and ...
A new deep learning system distills a high-accuracy pose estimation model into a lightweight edge-deployable AI coach that corrects athletes' ...
A redesigned YOLOv11n network recognizes lying, standing, eating and drinking in dense sheep flocks in real time while running on ...
Researchers compressed transformer-based tabular neural networks by up to 38-fold using knowledge distillation and deployed them on an NVIDIA Jetson ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine