Optimized DeepLabv3+ pipeline improves athlete boundary segmentation in four sports
A computational study of gymnastics, weightlifting, diving and sprinting footage reported that an optimized DeepLabv3+ pipeline achieved 88.31% mIoU and ...
A computational study of gymnastics, weightlifting, diving and sprinting footage reported that an optimized DeepLabv3+ pipeline achieved 88.31% mIoU and ...
An Ecuadorian research team has built HistoBreastCAD, an integrated deep learning framework that segments tissue regions, classifies breast histopathology into ...
Researchers have developed a two-stage attention-enhanced deep learning framework that segments breast lesions in ultrasound images before classifying them, achieving ...
A cascaded deep learning system combining DeepLabv3+ segmentation with ResNet18 classification can distinguish acceleration from deceleration craniocerebral injuries on CT ...
Researchers combined aerial image segmentation and camera-based object detection to build the first corridor-wide, AI-driven indicators of parking supply and ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine