Semi-supervised understanding of complex activities from temporal concepts

CF Crispim-Junior, M Koperski, S Cosar… - … on Advanced Video …, 2016 - inria.hal.science
Methods for action recognition have evolved considerably over the past years and can now
automatically learn and recognize short term actions with satisfactory accuracy.
Nonetheless, the recognition of complex activities-compositions of actions and scene
objects-is still an open problem due to the complex temporal and composite structure of this
category of events. Existing methods focus either on simple activities or oversimplify the
modeling of complex activities by targeting only whole-part relations between its sub-parts …

Semi-supervised understanding of complex activities from temporal concepts

CF Crispim, M Koperski, S Cosar… - 2016 13th IEEE …, 2016 - ieeexplore.ieee.org
Methods for action recognition have evolved considerably over the past years and can now
automatically learn and recognize short term actions with satisfactory accuracy.
Nonetheless, the recognition of complex activities-compositions of actions and scene
objects-is still an open problem due to the complex temporal and composite structure of this
category of events. Existing methods focus either on simple activities or oversimplify the
modeling of complex activities by targeting only whole-part relations between its sub-parts …
以上显示的是最相近的搜索结果。 查看全部搜索结果

Google学术搜索按钮

example.edu/paper.pdf
查找
获取 PDF 文件
引用
References