Computer Vision Framework Predicts Jianzi Trajectories and Hitting Types in Tests
Researchers developed a computer vision and pose estimation framework combining YOLOv8s localization and 17-keypoint skeleton tracking to jointly predict jianzi ...
Researchers developed a computer vision and pose estimation framework combining YOLOv8s localization and 17-keypoint skeleton tracking to jointly predict jianzi ...
A new study proposes a TD3-based intelligent terminal guidance law that uses Bi-LSTM trajectory prediction to improve missile interception of ...
A new conditional diffusion framework called CDJMP predicts multi-agent vehicle trajectories with state-of-the-art accuracy while cutting inference time to under ...
A new study combines TD3 reinforcement learning for drag coefficient identification with an attention-based BiLSTM that cuts trajectory prediction error ...
The KDDHCBT system achieved higher tested accuracy and processing speeds than three comparison models on internal RFID vehicle trajectories and ...
A YOLOv5-LiDAR basketball-robot system achieved 97.85% detection accuracy and high task-success rates in controlled dataset evaluations and simulations, with extreme ...
Researchers in China have built a two-layer bidirectional LSTM network that predicts a navigation buoy's position one hour ahead with ...
Researchers in China have developed an improved deep reinforcement learning framework that jointly optimizes trajectory prediction and lane-changing decisions, achieving ...
A new computational framework enables autonomous drones to identify driver behavior styles, quantify air-ground collision risk in real time, and ...
NASA Ames researchers built an LLM-based aviation decision-support system that routes natural language queries through nine validated expert models, achieving ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine