Sciweavers

2598 search results - page 16 / 520
» New Features to Identify Computer Generated Images
Sort
View
AAAI
2008
15 years 7 hour ago
Concept-Based Feature Generation and Selection for Information Retrieval
Traditional information retrieval systems use query words to identify relevant documents. In difficult retrieval tasks, however, one needs access to a wealth of background knowled...
Ofer Egozi, Evgeniy Gabrilovich, Shaul Markovitch
79
Voted
BMVC
2000
14 years 11 months ago
A New Method for Computing Optical Flow
Accurate and high density estimation of optical flow vectors in an image sequence is accomplished by a method that estimates the velocity distribution function for small overlappi...
W. F. Clocksin
SDM
2009
SIAM
205views Data Mining» more  SDM 2009»
15 years 6 months ago
Identifying Information-Rich Subspace Trends in High-Dimensional Data.
Identifying information-rich subsets in high-dimensional spaces and representing them as order revealing patterns (or trends) is an important and challenging research problem in m...
Chandan K. Reddy, Snehal Pokharkar
ICPR
2002
IEEE
15 years 10 months ago
Usefulness of Boundary Sequences in Computing Shape Features for Arbitrary Shaped Regions
A boundary sequence is a good representation of arbitrary shaped regions, but not directly used in computing shape features such as area, centroid, orientation, and so forth. In t...
Seongok Kim, Sungyoung Kim, Jongmin Kim, Minhwan K...
96
Voted
ECCV
2010
Springer
14 years 10 months ago
Object Recognition with Hierarchical Stel Models
Abstract. We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment ...
Alessandro Perina, Nebojsa Jojic, Umberto Castella...