Sciweavers

683 search results - page 52 / 137
» Using High-Level Semantic Features in Video Retrieval
Sort
View
ICCV
2001
IEEE
15 years 11 months ago
Learning the Semantics of Words and Pictures
We present a statistical model for organizing image collections which integrates semantic information provided by associated text and visual information provided by image features...
Kobus Barnard, David A. Forsyth
ICDE
2006
IEEE
191views Database» more  ICDE 2006»
15 years 11 months ago
Query Decomposition: A Multiple Neighborhood Approach to Relevance Feedback Processing in Content-based Image Retrieval
Today's Content-Based Image Retrieval (CBIR) techniques are based on the "k-nearest neighbors" (kNN) model. They retrieve images from a single neighborhood using lo...
Kien A. Hua, Ning Yu, Danzhou Liu
92
Voted
SIGIR
2009
ACM
15 years 4 months ago
Automatic video tagging using content redundancy
The analysis of the leading social video sharing platform YouTube reveals a high amount of redundancy, in the form of videos with overlapping or duplicated content. In this paper,...
Stefan Siersdorfer, José San Pedro, Mark Sa...
MM
2005
ACM
123views Multimedia» more  MM 2005»
15 years 3 months ago
Early versus late fusion in semantic video analysis
Semantic analysis of multimodal video aims to index segments of interest at a conceptual level. In reaching this goal, it requires an analysis of several information streams. At s...
Cees Snoek, Marcel Worring, Arnold W. M. Smeulders
96
Voted
MM
2005
ACM
171views Multimedia» more  MM 2005»
15 years 3 months ago
Semantic manifold learning for image retrieval
Learning the user’s semantics for CBIR involves two different sources of information: the similarity relations entailed by the content-based features, and the relevance relatio...
Yen-Yu Lin, Tyng-Luh Liu, Hwann-Tzong Chen