Sciweavers

844 search results - page 88 / 169
» From Motion Observation to Qualitative Motion Representation
Sort
View
CVPR
2012
IEEE
11 years 11 months ago
Learning object class detectors from weakly annotated video
Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from realworld w...
Alessandro Prest, Christian Leistner, Javier Civer...
ECCV
2010
Springer
14 years 2 months ago
Human Attributes from 3D Pose Tracking
We show that, from the output of a simple 3D human pose tracker one can infer physical attributes (e.g., gender and weight) and aspects of mental state (e.g., happiness or sadness)...
TOG
2008
235views more  TOG 2008»
13 years 9 months ago
Articulated mesh animation from multi-view silhouettes
Details in mesh animations are difficult to generate but they have great impact on visual quality. In this work, we demonstrate a practical software system for capturing such deta...
Daniel Vlasic, Ilya Baran, Wojciech Matusik, Jovan...
SPEECH
1998
215views more  SPEECH 1998»
13 years 8 months ago
3D lip shapes from video: A combined physical-statistical model
Tracking human lips in video is an important but notoriously dicult task. To accurately recover their motions in 3D from any head pose is an even more challenging task, though s...
Sumit Basu, Nuria Oliver, Alex Pentland
CRV
2009
IEEE
217views Robotics» more  CRV 2009»
14 years 3 months ago
Probabilistic 3D Tracking: Rollator Users' Leg Pose from Coronal Images
Understanding the human gait is an important objective towards improving elderly mobility. In turn, gait analyses largely depend on kinematic and dynamic measurements. While the m...
Samantha Ng, Adel H. Fakih, Adam Fourney, Pascal P...