We present a novel method for record extraction from social streams such as Twitter. Unlike typical extraction setups, these environments are characterized by short, one sentence ...
3D object recognition in scenes with occlusion and clutter is a difficult task. In this paper, we introduce a method that exploits the geometric scale-variability to aid in this ...
Study of contrast sensitivity of the human eye shows that our contrast discrimination sensitivity follows the weber law for suprathreshold levels. In this paper, we apply this fac...
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
Whereas most existing action recognition methods require computationally demanding feature extraction and/or classification, this paper presents a novel real-time solution that ut...