Abstract
The grasp type provides crucial information about hu-man action. However, recognizing the grasp type from un-constrained scenes is challenging because of the large vari-ations in appearance, occlusions and geometric distortions.In this paper, first we present a convolutional neural net-work to classify functional hand grasp types. Experimentson a public static scene hand data set validate good perfor-mance of the presented method. Then we present two applications utilizing grasp type classification: (a) inference of human action intention and (b) fine level manipulation action segmentation. Experiments on both tasks demonstratethe usefulness of grasp type as a cognitive feature for com-puter vision. This study shows that the grasp type is a powerful symbolic representation for action understanding, and thus opens new avenues for future research.