Sciweavers

CVPR
2007
IEEE
15 years 5 days ago
The effective resolution of correlation filters applied to natural scenes
In this paper, we measure the responses of image patches, used as filters, on different image ensembles and examine how the responses are affected by reducing the resolution of th...
Michel Vidal-Naquet, Manabu Tanifuji
CVPR
2007
IEEE
15 years 5 days ago
Nonnegative Tucker Decomposition
Nonnegative tensor factorization (NTF) is a recent multiway (multilinear) extension of nonnegative matrix factorization (NMF), where nonnegativity constraints are imposed on the C...
Yong-Deok Kim, Seungjin Choi
CVPR
2007
IEEE
15 years 5 days ago
Joint Real-time Object Detection and Pose Estimation Using Probabilistic Boosting Network
In this paper, we present a learning procedure called probabilistic boosting network (PBN) for joint real-time object detection and pose estimation. Grounded on the law of total p...
Jingdan Zhang, Shaohua Kevin Zhou, Leonard McMilla...
CVPR
2007
IEEE
15 years 5 days ago
Sensor noise modeling using the Skellam distribution: Application to the color edge detection
In this paper, we introduce the Skellam distribution as a sensor noise model for CCD or CMOS cameras. This is derived from the Poisson distribution of photons that determine the s...
Youngbae Hwang, Jun-Sik Kim, In-So Kweon
CVPR
2007
IEEE
15 years 5 days ago
OpenVL: Towards A Novel Software Architecture for Computer Vision
This paper presents our progress on OpenVL - a novel software architecture to address efficiency through facilitating hardware acceleration, reusability and scalability for comput...
Changsong Shen, S. Sidney Fels, James J. Little
CVPR
2007
IEEE
15 years 5 days ago
Scaled Motion Dynamics for Markerless Motion Capture
This work proposes a way to use a-priori knowledge on motion dynamics for markerless human motion capture (MoCap). Specifically, we match tracked motion patterns to training patte...
Bodo Rosenhahn, Thomas Brox, Hans-Peter Seidel
CVPR
2007
IEEE
15 years 5 days ago
A Hierarchical Model of Shape and Appearance for Human Action Classification
We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic...
Juan Carlos Niebles, Fei-Fei Li 0002
CVPR
2007
IEEE
15 years 5 days ago
Groupwise Shape Registration on Raw Edge Sequence via A Spatio-Temporal Generative Model
Groupwise shape registration of raw edge sequence is addressed. Automatically extracted edge maps are treated as noised input shape of the deformable object and their registration...
Huijun Di, Rao Naveed Iqbal, Guangyou Xu, Linmi Ta...
CVPR
2007
IEEE
15 years 5 days ago
Unsupervised Learning of Image Transformations
Roland Memisevic, Geoffrey E. Hinton
CVPR
2007
IEEE
15 years 5 days ago
Complex Salient Regions for Computer Vision Problems
Sergio Escalera, Petia Radeva, Oriol Pujol