In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represent...
This paper forms a continuation of our work focused on exploiting film grammar for the task of automated film understanding. We examine film rhythm, a powerful narrative concept u...
Abstract. This paper presents an approach to large lexicon sign recognition that does not require tracking. This overcomes the issues of how to accurately track the hands through s...
- In this paper we present a specific matching technique based on basic motor patterns between two image sequences taken from different view points and a VRML synthetic human model...
Jose Maria Buades Rubio, Ramon Mas, Francisco J. P...
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...