Sciweavers

ACCV
2007
Springer
13 years 10 months ago
MAPACo-Training: A Novel Online Learning Algorithm of Behavior Models
The traditional co-training algorithm, which needs a great number of unlabeled examples in advance and then trains classifiers by iterative learning approach, is not suitable for ...
Heping Li, Zhanyi Hu, Yihong Wu, Fuchao Wu
ACCV
2007
Springer
13 years 10 months ago
Texture-Independent Feature-Point Matching (TIFM) from Motion Coherence
Abstract. This paper proposes a novel and efficient feature-point matching algorithm for finding point correspondences between two uncalibrated images. The striking feature of th...
Ping Li, Dirk Farin, Rene Klein Gunnewiek, Peter H...
ACCV
2007
Springer
13 years 10 months ago
Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates
Shiro Kumano, Kazuhiro Otsuka, Junji Yamato, Eisak...
ACCV
2007
Springer
13 years 10 months ago
Detecting and Segmenting Un-occluded Items by Actively Casting Shadows
We present a simple and practical approach for segmenting un-occluded items in a scene by actively casting shadows. By ’items’, we refer to objects (or part of objects) enclose...
Tze Ki Koh, Amit K. Agrawal, Ramesh Raskar, Steve ...
ACCV
2007
Springer
13 years 10 months ago
Robust Foreground Extraction Technique Using Gaussian Family Model and Multiple Thresholds
Abstract. We propose a robust method to extract silhouettes of foreground objects from color video sequences. To cope with various changes in the background, the background is mode...
Hansung Kim, Ryuuki Sakamoto, Itaru Kitahara, Tomo...
ACCV
2007
Springer
13 years 10 months ago
Gesture Recognition Under Small Sample Size
This paper addresses gesture recognition under small sample size, where direct use of traditional classifiers is difficult due to high dimensionality of input space. We propose a ...
Tae-Kyun Kim, Roberto Cipolla
ACCV
2007
Springer
13 years 10 months ago
A Theoretical Approach to Construct Highly Discriminative Features with Application in AdaBoost
AdaBoost is a practical method of real-time face detection, but abides by a crucial problem of overfitting for the big number of features used in a trained classifier due to the ...
Yuxin Jin, Linmi Tao, Guangyou Xu, Yuxin Peng
ACCV
2007
Springer
13 years 10 months ago
Learning Generative Models for Monocular Body Pose Estimation
We consider the problem of monocular 3d body pose tracking from video sequences. This task is inherently ambiguous. We propose to learn a generative model of the relationship of bo...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
ACCV
2007
Springer
13 years 10 months ago
Hand Posture Estimation in Complex Backgrounds by Considering Mis-match of Model
This paper proposes a novel method of estimating 3-D hand posture from images observed in complex backgrounds. Conventional methods often cause mistakes by mis-matches of local ima...
Akihiro Imai, Nobutaka Shimada, Yoshiaki Shirai
ACCV
2007
Springer
13 years 10 months ago
Calibrating Pan-Tilt Cameras with Telephoto Lenses
Abstract. Pan-tilt cameras are widely used in surveillance networks. These cameras are often equipped with telephoto lenses to capture objects at a distance. Such a camera makes fu...
Xinyu Huang, Jizhou Gao, Ruigang Yang