Sciweavers

1546 search results - page 96 / 310
» Computing Pose Sequences Directly from Videos
Sort
View
ECCV
2002
Springer
14 years 10 months ago
Automatic Detection and Tracking of Human Motion with a View-Based Representation
Abstract. This paper proposes a solution for the automatic detection and tracking of human motion in image sequences. Due to the complexity of the human body and its motion, automa...
Ronan Fablet, Michael J. Black
CVPR
2011
IEEE
13 years 19 days ago
Nonlinear Shape Manifolds as Shape Priors in Level Set Segmentation and Tracking
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level setbased segmentation and tracking. Unlike previous work, we represent sha...
Victor Prisacariu, Ian Reid
ICIP
2008
IEEE
14 years 10 months ago
Activity-based temporal segmentation for videos of interacting objects using invariant trajectory features
This paper presents a content-based approach for temporal segmentation of videos. Tracked objects are characterized by their 2D trajectories which are used in a meaningful way to ...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
CVPR
2010
IEEE
14 years 2 months ago
Learning 3D Action Models from a few 2D videos for View Invariant Action Recognition
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
Pradeep Natarajan, Vivek Singh, Ram Nevatia
ICPR
2004
IEEE
14 years 10 months ago
Selecting Models from Videos for Appearance-Based Face Recognition
In this paper, we propose an unsupervised approach to select representative face samples (models) from raw videos and build an appearance-based face recognition system. The approa...
Abdenour Hadid, Matti Pietikäinen