Sciweavers

571 search results - page 97 / 115
» One person labels one million images
Sort
View
ECCV
2008
Springer
14 years 10 months ago
Improving People Search Using Query Expansions
In this paper we are interested in finding images of people on the web, and more specifically within large databases of captioned news images. It has recently been shown that visua...
Thomas Mensink, Jakob J. Verbeek
CVPR
2007
IEEE
14 years 10 months ago
Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data
A popular approach to problems in image classification is to represent the image as a bag of visual words and then employ a classifier to categorize the image. Unfortunately, a si...
Liu Yang, Rong Jin, Caroline Pantofaru, Rahul Sukt...
IJCV
2006
171views more  IJCV 2006»
13 years 8 months ago
Combining Generative and Discriminative Models in a Framework for Articulated Pose Estimation
We develop a method for the estimation of articulated pose, such as that of the human body or the human hand, from a single (monocular) image. Pose estimation is formulated as a s...
Rómer Rosales, Stan Sclaroff
KDD
2010
ACM
286views Data Mining» more  KDD 2010»
13 years 6 months ago
Nonnegative shared subspace learning and its application to social media retrieval
Although tagging has become increasingly popular in online image and video sharing systems, tags are known to be noisy, ambiguous, incomplete and subjective. These factors can ser...
Sunil Kumar Gupta, Dinh Q. Phung, Brett Adams, Tru...
ICIP
2008
IEEE
14 years 10 months ago
Cross-domain learning methods for high-level visual concept classification
Exploding amounts of multimedia data increasingly require automatic indexing and classification, e.g. training classifiers to produce high-level features, or semantic concepts, ch...
Wei Jiang, Eric Zavesky, Shih-Fu Chang, Alexander ...