This paper proposes an efficient and simple method for identity recognition in uncontrolled videos. The idea is to use images collected from the web to learn representations of actions related with identity, use this knowledge to automatically annotate identity in videos. Our approach is unsupervised where it can identify the identity of human in the video like YouTube directly through the knowledge of his actions. Its benefits are two-fold: 1) we can improve retrieval of identity images, and 2) we can collect a database of action poses related with identity, which can then be used in tagging videos. We present the simple experimental evidence that using action images related with identity collected from the web, annotating identity is possible.