Progress in action recognition has been in large part due to advances in the features that drive learning-based methods. However, the relative sparsity of training data and the ri...
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...
In recent years high quality interaction devices have become very popular in our environment. The industries are also currently undergoing rapid change and various technologies hav...
Nam Woo Kim, Seung Jae Lee, Byung-Gook Lee, Joon-J...
We propose human action detection based on a successive convex matching scheme. Human actions are represented as sequences of postures and specific actions are detected in video b...
In this paper, we approach the problem of understanding human actions from still images. Our method involves representing the pose with a spatial and orientational histogramming o...
Nazli Ikizler, Pinar Duygulu, Ramazan Gokberk Cinb...