Sciweavers

27 search results - page 5 / 6
» Multiple Bernoulli Relevance Models for Image and Video Anno...
Sort
View
ICASSP
2009
IEEE
13 years 12 months ago
Multi-view tracking of articulated human motion in silhouette and pose manifolds
This paper presents a multi-view articulated human motion tracking framework using particle filter with manifold learning through Gaussian process latent variable model. The dime...
Feng Guo, Gang Qian
ICIP
2007
IEEE
14 years 7 months ago
Hierarchical Feature Fusion for Visual Tracking
A new method for object tracking in video sequences is presented. This method exploits the benefits of particle filters to tackle the multimodal distributions emerging from clutte...
Alexandros Makris, Dimitrios I. Kosmopoulos, Stavr...
AAAI
2010
13 years 6 months ago
Visual Contextual Advertising: Bringing Textual Advertisements to Images
Advertising in the case of textual Web pages has been studied extensively by many researchers. However, with the increasing amount of multimedia data such as image, audio and vide...
Yuqiang Chen, Ou Jin, Gui-Rong Xue, Jia Chen, Qian...
CVPR
2011
IEEE
13 years 1 months ago
Interactively Building a Discriminative Vocabulary of Nameable Attributes
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
Devi Parikh, Kristen Grauman
KDD
2009
ACM
219views Data Mining» more  KDD 2009»
14 years 5 months ago
Structured correspondence topic models for mining captioned figures in biological literature
A major source of information (often the most crucial and informative part) in scholarly articles from scientific journals, proceedings and books are the figures that directly pro...
Amr Ahmed, Eric P. Xing, William W. Cohen, Robert ...