Tag: computer vision

Researchers at the Norwegian University of Science and Technology have developed two new explainability methods that integrate transformer attention weights ...

Researchers have developed CNN-SA-RFR, a cosine similarity-based self-attention framework that suppresses redundant filters during CNN training, boosting plant disease classification ...

A new robust learning framework from Zhejiang University addresses identity misalignment in unsupervised visible-infrared person re-identification, improving cross-modality retrieval under ...

Researchers have developed a single-arm robotic sewing system that combines computer vision, neural-network grasp estimation, and force control to handle ...

A new explainable deep learning framework segments marine biofouling at the pixel level, improving underwater inspection accuracy and structural health ...

A new special issue in Medical & Biological Engineering & Computing showcases how deep learning is transforming ultrasound image segmentation, ...

A new Communications Engineering study formalizes when frame-based and event-based visual data each hold a fundamental information advantage and how ...

A scoping review of 129 studies finds wearable inertial sensors dominate rhythm-relevant sports technology while auditory and haptic feedback channels ...

Researchers in Slovakia have built SMaRTAban, a voice-controlled large language model agent that lets a quadruped robot understand spoken English ...

A new comparative study finds that YOLO-World v2 offers the best balance of accuracy, speed, and prompt robustness among open-vocabulary ...