2011 · 39 citations · 15 references
ComputingComputer ScienceComputer VisionHuman BehaviorVisual AnalyticsAction RecognitionAction RepresentationGraph-based LearningGraphical RepresentationPose EstimationActivity RecognitionGraph-based Action RecognitionGraphical Model LearningHuman Pose EstimationPose-based Action Recognition
Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven approach to human analysis. In this work we aim to explore this approach using the large amount of images spanning a subspace of human appearance. We model this subspace by connecting images into a graph and propagating information through such a graph using a discriminatively-trained graphical model. We particularly address the problems of human pose estimation and action recognition and demonstrate how image graphs help solving these problems jointly. We report results on still images with human actions from the KTH dataset.
15
Pattern Recognition and Machine Learning
Journal of Electronic Imaging · 2007 · 22.1K citations
Making Large-Scale SVM Learning Practical
Thorsten Joachims · Technical reports · 2006 · 4.3K citations · Full text