Sciweavers

4234 search results - page 583 / 847
» A Method for Web Information Extraction
Sort
View
CVPR
2010
IEEE
16 years 19 days ago
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Adriana Kovashka, Kristen Grauman
ACCV
2009
Springer
15 years 11 months ago
Highly-Automatic MI Based Multiple 2D/3D Image Registration Using Self-initialized Geodesic Feature Correspondences
Abstract. Intensity based registration methods, such as the mutual information (MI), do not commonly consider the spatial geometric information and the initial correspondences are ...
Hongwei Zheng, Ioan Cleju, Dietmar Saupe
AAI
2006
215views more  AAI 2006»
15 years 4 months ago
Extensive Evaluation of Efficient NLP-Driven Text Classification
Extensive experimental evidence is required to study the impact of text categorization approaches on real data and to assess the performance within operational scenarios. In this ...
Roberto Basili, Alessandro Moschitti, Maria Teresa...
148
Voted
ACCV
2009
Springer
15 years 8 months ago
People Tracking and Segmentation Using Efficient Shape Sequences Matching
Abstract. We design an effective shape prior embedded human silhouettes extraction algorithm. Human silhouette extraction is found challenging because of articulated structures, po...
Junqiu Wang, Yasushi Yagi, Yasushi Makihara
MVA
2007
211views Computer Vision» more  MVA 2007»
15 years 5 months ago
Vision-based UAV Navigation in Mountain Area
Most vision-based UAV (Unmanned Aerial Vehicle) navigation algorithms extract manmade features such as buildings or roads, which are well structured in urban terrain, using the CC...
Jihwan Woo, Kilho Son, Teng Li, Gwan Sung Kim, In-...