BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Souad Mohaoui (Örebro University) DTSTART:20250331T111500Z DTEND:20250331T120000Z DTSTAMP:20260417T003352Z UID:cam/71 DESCRIPTION:Title: Ten sor decomposition approaches for motion capture data completion.\nby S ouad Mohaoui (Örebro University) as part of CAM seminar\n\nLecture held i n MV:L14.\n\nAbstract\nTensor decompositions are powerful tools for analyz ing high-dimensional data by breaking down multi-way arrays into smaller\, meaningful components. They help uncover patterns and handle missing data effectively. In this work\, we consider two tensor decomposition methods\ , CANDECOMP/PARAFAC (CP) and Tucker\, to address the problem of gap fillin g in motion capture (MoCap) data. The gap-filling problem in marker-based MoCap systems occurs when markers become occluded or detached during recor ding\, resulting in incomplete data. Tensor decompositions offer an effect ive solution by leveraging the inherent multi-way structure of MoCap data. We develop and analyze different completion algorithms built upon CP and Tucker decompositions\, and evaluate their performance across different mi ssing data scenarios. The algorithms are tested using motion capture seque nces from the publicly available CMU and HDM05 datasets.\n LOCATION:https://researchseminars.org/talk/cam/71/ END:VEVENT END:VCALENDAR