73 search results - page 6 / 15 » Unsupervised Improvement of Visual Detectors using Co-Traini... |
MM
2009
ACM
15 years 4 months ago
2009
ACM
The following paper presents a novel audio-visual approach for unsupervised speaker locationing. Using recordings from a single, low-resolution room overview camera and a single f...
84
Voted
ICCV
2009
IEEE
16 years 2 months ago
2009
IEEE
We present a method to learn visual attributes (eg.“red”,
“metal”, “spotted”) and object classes (eg. “car”,
“dress”, “umbrella”) together. We assume imag...
ICCV
2009
IEEE
16 years 2 months ago
2009
IEEE
Common visual codebook generation methods used in
a Bag of Visual words model, e.g. k-means or Gaussian
Mixture Model, use the Euclidean distance to cluster features
into visual...
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
WSC
2004
14 years 11 months ago
2004
To improve its process modeling capabilities, Los Alamos has worked toward integrating dose modeling tools with advanced discrete-event simulation tools. To date, dose information...