Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
The present paper describes a robust approach for abbreviating terms. First, in order to incorporate non-local information into abbreviation generation tasks, we present both impl...
In this paper we explore the idea of using high-level semantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the constr...