Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input.
About SportCaps :
SportsCap proposes a challenging sports dataset called Sports Motion and Recognition Tasks (SMART) dataset, which contains per-frame action labels, manually annotated pose, and action assessment of various challenging sports video clips from professional referees.
Their approaches :
This is especially prevalent in non-daily action classes like fitness and sports domains. This can be mitigated, for example, by annotating domain-specific datasets , but that requires a considerable amount of manual annotation efforts, financial resources, and 3D annotations can only be obtained in controlled conditions. Therefore, we propose to learn domain-specific pose-sensitive representations from unlabeled videos, which can be fine tuned using only a small labeled dataset. ...
Learn more about Monocular 3 D Human :
brainly.com/question/21602764
#SPJ4
