Researchers develop a novel vote-based model for more accurate hand-held object pose estimation
Peer-Reviewed Publication
Updates every hour. Last Updated: 12-May-2025 12:09 ET (12-May-2025 16:09 GMT/UTC)
Estimating the pose of hand-held objects is a critical and challenging problem in robotics and computer vision. While leveraging multi-modal RGB and depth data is a promising solution, existing approaches still face challenges due to hand-induced occlusions and multimodal data fusion. In a new study, researchers developed a novel deep learning framework that addresses these issues by introducing a novel vote-based fusion module and a hand-aware pose estimation module.
Vaccines save millions of lives every year, but there is still an urgent need for more efficient vaccines that target pathogens transmitted through the respiratory tract and may cause fatal infections. Research from the University of Oslo demonstrates that a new versatile vaccine technology, a needle-free, albumin-based vaccine platform, may be attractive for design of vaccines against multiple respiratory pathogens. Hopefully, this may pave the way for vaccines that provide not only systemic immunity, but also protection at the actual site of infection.
The intensification of existing farmland can sometimes be more harmful to local biodiversity than expanding the area covered by agricultural land, finds a new study led by University College London researchers.