Dual-Pooling Attention Gives YOLO a Sharper Eye for Crowded Streets
Researchers at IIITDM Kancheepuram have developed DECA-YOLO, a lightweight dual-pooling channel attention enhancement to YOLOv7 that improves real-time pedestrian detection ...
Researchers at IIITDM Kancheepuram have developed DECA-YOLO, a lightweight dual-pooling channel attention enhancement to YOLOv7 that improves real-time pedestrian detection ...
Researchers have developed MFKR Net, a lightweight deep learning model that identifies individuals from contactless middle finger knuckle images with ...
Researchers have devised a pooled AlphaFold3 screening strategy that cuts the number of computational jobs needed to map an entire ...
Researchers have developed a cross-temporal attention network that fuses short-term motion and long-term behavioral cues to recognize gun threats, aggression, ...
Japanese researchers trained a 3D Vision Transformer foundation model on postmortem CT scans of nearly 1,500 femora, achieving over 90 ...
A systematic review of 180 publications argues that AI tools are reorganizing visibility and authority in art history, producing an ...
Researchers in China have developed MSEA, a CLIP-based framework that combines multi-scale convolutions and efficient linear attention to achieve record ...
A systematic review of 131 studies finds that deep learning cameras can monitor pig welfare and behavior with over 95 ...
Researchers in China have developed MAF-Net, a multi-scale attention fusion network that achieves a record Dice score of 85.47 percent ...
Researchers in India have built an explainable deep learning framework that forecasts cloud host load in real time with about ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine