We consider the problem of human parsing with partbased models. Most previous work in part-based models only considers rigid parts (e.g. torso, head, half limbs) guided by human a...
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
Non-rigid structure from motion (NR-SFM) is a difficult, underconstrained problem in computer vision. This paper proposes a new algorithm that revises the standard matrix factori...
The co-occurrence pattern, a combination of binary or local features, is more discriminative than individual features and has shown its advantages in object, scene, and action rec...
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...