We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human a...
Persons may perform an activity in many different styles, or noise may cause an identical activity to have different temporal structures. We present a robust methodology for recog...
A low-cost active vision head with ten degrees of freedom is presented that has been build from off-the-shelf parts. To obtain high resolution depth information of fixated objects ...
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...