Most approaches to classifying media content assume a fixed, closed vocabulary of labels. In contrast, we advocate machine learning approaches which take advantage of the millions...
We present a novel method for modeling dynamic visual
phenomena, which consists of two key aspects. First, the in-
tegral motion of constituent elements in a dynamic scene is
ca...
In many image and video collections, we have access
only to partially labeled data. For example, personal photo
collections often contain several faces per image and a caption
t...
Benjamin Sapp, Benjamin Taskar, Chris Jordan, Timo...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Abstract. Several challenges remain in the effort to build software capable of conducting realtime dialogue with people. Part of the problem has been a lack of realtime flexibili...