Sciweavers

Share
CVPR
2012
IEEE
7 years 3 months ago
Unsupervised learning of translation invariant occlusive components
We study unsupervised learning of occluding objects in images of visual scenes. The derived learning algorithm is based on a probabilistic generative model which parameterizes obj...
Zhenwen Dai, Jörg Lücke
AMDO
2006
Springer
9 years 5 months ago
Human Motion Synthesis by Motion Manifold Learning and Motion Primitive Segmentation
Abstract. We propose motion manifold learning and motion primitive segmentation framework for human motion synthesis from motion-captured data. High dimensional motion capture date...
Chan-Su Lee, Ahmed M. Elgammal
ACII
2007
Springer
9 years 5 months ago
Detecting Affect from Non-stylised Body Motions
In this paper we present a novel framework for analysing non-stylised motion in order to detect implicitly communicated affect. Our approach makes use of a segmentation technique w...
Daniel Bernhardt, Peter Robinson
IROS
2008
IEEE
111views Robotics» more  IROS 2008»
9 years 7 months ago
Motion primitives for a tumbling robot
— The desire for a high mobility-to-size ratio in mobile robots has led to the exploration of many new methods of locomotion, one of which is tumbling. To the authors’ knowledg...
Brett Hemes, Duc Fehr, Nikolaos Papanikolopoulos
IROS
2008
IEEE
142views Robotics» more  IROS 2008»
9 years 7 months ago
Scaffolding on-line segmentation of full body human motion patterns
Abstract— This paper develops an approach for on-line segmentation of whole body human motion patterns during human motion observation and learning. A Hidden Markov Model is used...
Dana Kulic, Yoshihiko Nakamura
ICRA
2008
IEEE
191views Robotics» more  ICRA 2008»
9 years 8 months ago
Combining automated on-line segmentation and incremental clustering for whole body motions
Abstract— This paper describes a novel approach for incremental learning of human motion pattern primitives through on-line observation of human motion. The observed motion time ...
Dana Kulic, Wataru Takano, Yoshihiko Nakamura
CVPR
2009
IEEE
9 years 8 months ago
Trajectory parsing by cluster sampling in spatio-temporal graph
The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
Xiaobai Liu, Liang Lin, Song Chun Zhu, Hai Jin
books