Sciweavers

617 search results - page 8 / 124
» A Method for Text Localization and Recognition in Real-World...
Sort
View
PCM
2010
Springer
204views Multimedia» more  PCM 2010»
13 years 5 months ago
Learning Contextual Metrics for Automatic Image Annotation
Abstract. The semantic contextual information is shown to be an important resource for improving the scene and image recognition, but is seldom explored in the literature of previo...
Zuotao Liu, Xiangdong Zhou, Yu Xiang, Yan-Tao Zhen...
CIKM
2005
Springer
14 years 7 days ago
Predicting accuracy of extracting information from unstructured text collections
Exploiting lexical and semantic relationships in large unstructured text collections can significantly enhance managing, integrating, and querying information locked in unstructur...
Eugene Agichtein, Silviu Cucerzan
ICIAP
2007
ACM
14 years 6 months ago
Appearance-based 3D object recognition with time-invariant features
In this paper we explore the interlink between temporally dense view-based object recognition and sparse image representations with local keypoints. The temporal component is an a...
Elisabetta Delponte, Nicoletta Noceti, Francesca O...
TVCG
2012
218views Hardware» more  TVCG 2012»
11 years 9 months ago
Flow-Based Local Optimization for Image-to-Geometry Projection
—The projection of a photographic dataset on a 3D model is a robust and widely applicable way to acquire appearance information of an object. The first step of this procedure is...
Matteo Dellepiane, Ricardo Marroquim, Marco Callie...
MM
2010
ACM
196views Multimedia» more  MM 2010»
13 years 7 months ago
Non-parametric anomaly detection exploiting space-time features
In this paper a real-time anomaly detection system for video streams is proposed. Spatio-temporal features are exploited to capture scene dynamic statistics together with appearan...
Lorenzo Seidenari, Marco Bertini