Sciweavers

CVPR
2010
IEEE
14 years 1 months ago
Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer
Learning object categories from small samples is a challenging problem, where machine learning tools can in general provide very few guarantees. Exploiting prior knowledge may be ...
Tatiana Tommasi, Francesco Orabona, Barbara Caputo
CVPR
2010
IEEE
1639views Computer Vision» more  CVPR 2010»
14 years 1 months ago
Multi-Target Tracking of Time-varying Spatial Patterns
Time-varying spatial patterns are common, but few computational tools exist for discovering and tracking multiple, sometimes overlapping, spatial structures of targets. We propose...
Jingchen Liu, Yanxi Liu
CVPR
2010
IEEE
14 years 1 months ago
Learning Shift-Invariant Sparse Representation of Actions
A central problem in the analysis of motion capture (Mo- Cap) data is how to decompose motion sequences into primitives. Ideally, a description in terms of primitives should fac...
Yi Li
CVPR
2010
IEEE
14 years 1 months ago
Fast and Robust Object Segmentation with the Integral Linear Classifier
We propose an efficient method, built on the popular Bag of Features approach, that obtains robust multiclass pixellevel object segmentation of an image in less than 500ms, with...
David Aldavert, Arnau Ramisa, Ricardo Toledo, Ramo...
CVPR
2010
IEEE
14 years 1 months ago
Fast Approximate Energy Minimization with Label Costs
The α-expansion algorithm [4] has had a significant impact in computer vision due to its generality, effectiveness, and speed. Thus far it can only minimize energies that involv...
Andrew Delong, Anton Osokin, Hossam Isack, Yuri Bo...
CVPR
2010
IEEE
14 years 1 months ago
Automatic Point-based Facial Trait Judgments Evaluation
Humans constantly evaluate the personalities of other people using their faces. Facial trait judgments have been studied in the psychological field, and have been determined to i...
Mario Rojas, David Masip, jordi Vitria
CVPR
2010
IEEE
14 years 1 months ago
Clustering Dynamic Textures with the Hierarchical EM Algorithm
The dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS). The DT model ...
Antoni Chan, Emanuele Coviello, Gert Lanckriet
CVPR
2010
IEEE
14 years 1 months ago
Object-Graphs for Context-Aware Category Discovery
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
Yong Jae Lee, Kristen Grauman
CVPR
2010
IEEE
14 years 1 months ago
Posture Invariant Surface Description and Feature Extraction
We propose a posture invariant surface descriptor for triangular meshes. Using intrinsic geometry, the surface is first transformed into a representation that is independent of t...
Stefanie Wuhrer, Zouhour Ben Azouz, Chang Shu
CVPR
2010
IEEE
14 years 1 months ago
Figure-Ground Segmentation Improves Handled Object Recognition in Egocentric Video
Identifying handled objects, i.e. objects being manipulated by a user, is essential for recognizing the person’s activities. An egocentric camera as worn on the body enjoys many...
Xiaofeng Ren, Chunhui Gu