77
edits
Changes
no edit summary
|-
|-
| March 5
| March 5
| "Snow Break"
|
|-
| March 12
| Yezhou Yang
| Yezhou Yang
| Grasp Type Revisited: A Modern Perspective on A Classical Feature for Vision and Robotics
| Grasp Type Revisited: A Modern Perspective on A Classical Feature for Vision and Robotics
|-
|-
| March 19
| March 19
|-
|-
| April 2
| April 2
| Joe Ng
| Bahadir Ozdemir
| TBD
| TBD
|-
|-
|-
|-
| April 30
| April 30
| Aleksandr (?)
| Joe Ng
| TBD
| TBD
|-
|-
| May 7
| May 7
| Francisco (?)
| Aleksandr(?), Francisco (?)
| TBD
| TBD
|-
|-
===Grasp Type Revisited: A Modern Perspective on A Classical Feature for Vision and Robotics===
===Grasp Type Revisited: A Modern Perspective on A Classical Feature for Vision and Robotics===
Speaker: [http://www.umiacs.umd.edu/~yzyang/ Yezhou Yang] -- Date: March 5, 2015
Speaker: [http://www.umiacs.umd.edu/~yzyang/ Yezhou Yang] -- Date: March 13, 2015
Abstract: Our ability to interpret other people's actions hinges crucially on predictions about their intentionality. The grasp type provides crucial information about human action. However, recognizing the grasp type from unconstrained scenes is challenging because of the large variations in appearance, occlusions and geometric distortions. In this paper, first we present a convolutional neural network to classify functional hand grasp types. Experiments on a public static scene hand data set validate good performance 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.
Abstract: Our ability to interpret other people's actions hinges crucially on predictions about their intentionality. The grasp type provides crucial information about human action. However, recognizing the grasp type from unconstrained scenes is challenging because of the large variations in appearance, occlusions and geometric distortions. In this paper, first we present a convolutional neural network to classify functional hand grasp types. Experiments on a public static scene hand data set validate good performance 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.