Sciweavers

CVPR
2009
IEEE
15 years 15 days ago
Discriminative Subvolume Search for Efficient Action Detection
Actions are spatio-temporal patterns which can be characterized by collections of spatio-temporal invariant features. Detection of actions is to find the re-occurrences (e.g. th...
Junsong Yuan (Northwestern University), Zicheng Li...
CVPR
2009
IEEE
15 years 15 days ago
Error Propagations for Local Bundle Adjustment
Local bundle adjustment (LBA) has recently been introduced to estimate the geometry of image sequences taken by a calibrated camera. Its advantage over standard (global) bundle ...
Alexandre Eudes (LASMEA & CEA LIST), Maxime L...
CVPR
2009
IEEE
15 years 15 days ago
Pose Estimation with Radial Distortion and Unknown Focal Length
This paper presents a solution to the problem of pose estimation in the presence of heavy radial distortion and a potentially large number of outliers. The main contribution is ...
Klas Josephson, Martin Byröd
CVPR
2009
IEEE
15 years 15 days ago
Linear Embeddings in Non-Rigid Structure From Motion
This paper proposes a method to recover the embedding of the possible shapes assumed by a deforming nonrigid object by comparing triplets of frames from an orthographic video se...
Vincent Rabaud (University of California, San Dieg...
CVPR
2009
IEEE
1010views Computer Vision» more  CVPR 2009»
15 years 15 days ago
A Family of Contextual Measures of Similarity between Distributions with Application to Image Retrieval
During this talk, I will introduce a novel family of contextual measures of similarity between distributions: the similarity between two distributions q and p is measured in the co...
Florent Perronnin (Xerox Research Centre Europe), ...
CVPR
2009
IEEE
15 years 15 days ago
An Empirical Bayes Approach to Contextual Region Classification
This paper presents a nonparametric approach to labeling of local image regions that is inspired by recent developments in information-theoretic denoising. The chief novelty of ...
Svetlana Lazebnik (UNC Chapel Hill), Maxim Raginsk...
CVPR
2009
IEEE
1382views Computer Vision» more  CVPR 2009»
15 years 15 days ago
Super-Resolution via Recapture and Bayesian Effect Modeling
This paper presents Bayesian edge inference (BEI), a single-frame super-resolution method explicitly grounded in Bayesian inference that addresses issues common to existing meth...
Bryan S. Morse, Dan Ventura, Kevin D. Seppi, Neil ...
CVPR
2009
IEEE
15 years 15 days ago
Planar Orientation from Blur Gradients in a Single Image
We present a focus-based method to recover the orientation of a textured planar surface patch from a single image. The method exploits the relationship between the orientation o...
Michael S. Langer, Scott McCloskey
CVPR
2009
IEEE
15 years 15 days ago
Angular Embedding: from Jarring Intensity Differences to Perceived Luminance
Our goal is to turn an intensity image into its perceived luminance without parsing it into depths, surfaces, or scene illuminations. We start with jarring intensity differences at...
Stella X. Yu
CVPR
2009
IEEE
15 years 15 days ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...