Sciweavers

76 search results - page 7 / 16
» Annotator Rationales for Visual Recognition
Sort
View
CVPR
2010
IEEE
13 years 7 months ago
Attribute-centric recognition for cross-category generalization
We propose an approach to find and describe objects within broad domains. We introduce a new dataset that provides annotation for sharing models of appearance and correlation acr...
Ali Farhadi, Ian Endres, Derek Hoiem
CVIU
2006
317views more  CVIU 2006»
13 years 7 months ago
A general method for human activity recognition in video
In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a f...
Neil Robertson, Ian D. Reid
CVPR
2009
IEEE
15 years 2 months 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...
WWW
2006
ACM
14 years 8 months ago
Image annotation using search and mining technologies
In this paper, we present a novel solution to the image annotation problem which annotates images using search and data mining technologies. An accurate keyword is required to ini...
Xin-Jing Wang, Lei Zhang, Feng Jing, Wei-Ying Ma
WWW
2006
ACM
14 years 8 months ago
Finding visual concepts by web image mining
We propose measuring "visualness" of concepts with images on the Web, that is, what extent concepts have visual characteristics. This is a new application of "Web i...
Keiji Yanai, Kobus Barnard