GitHub

Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models

Existing zero-shot temporal action detection (ZS-TAD) methods predominantly use fully supervised or unsuper- vised strategies to recognize unseen activities. However, these training-based methods are ...
IEEE

Transformer-Based Object Detection in Low-Altitude Maritime UAV Remote Sensing Images

Abstract: Object detection technology plays an essential role in uncrewed aerial vehicle (UAV) sea search and rescue missions, which aim to quickly locate crucial targets such as trapped people and ...
IEEE

Toward Model-Independent Separative Training for Deep Hyperspectral Anomaly Detection With Mask Guidance

Abstract: Hyperspectral anomaly detection (HAD) aims to recognize a minority of anomalies that are spectrally different from their surrounding background without prior knowledge. Deep neural networks ...
Medical Xpress

High-intensity training improves muscle function in inflammatory muscle disease, study suggests

High-intensity interval training boosts fitness and muscle endurance more effectively than traditional home exercise programs in people recently diagnosed with inflammatory muscle disease. That is the ...
Reuters

China's tech giants move AI model training overseas to access Nvidia chips, FT reports

Nov 27 (Reuters) - Top Chinese firms are training their artificial intelligence models abroad to access Nvidia's (NVDA.O), opens new tab chips and avoid U.S. measures aimed at curbing their progress ...