Sciweavers

22 search results - page 4 / 5
» Extremely fast text feature extraction for classification an...
Sort
View
SPIESR
2000
138views Database» more  SPIESR 2000»
13 years 7 months ago
Descriptor for spatial distribution of motion activity for compressed video
In this paper we present a new descriptor for spatial distribution of motion activity in video sequences. We construct a histogram of areas of distinct regions (or "blobs&quo...
Ajay Divakaran, Huifang Sun
BMVC
2010
13 years 4 months ago
Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests
Whereas most existing action recognition methods require computationally demanding feature extraction and/or classification, this paper presents a novel real-time solution that ut...
Tsz-Ho Yu, Tae-Kyun Kim, Roberto Cipolla
CACM
2000
225views more  CACM 2000»
13 years 6 months ago
Complementary Video and Audio Analysis for Broadcast News Archives
The Informedia Digital Video Library system extracts information from digitized video sources and allows full content search and retrieval over all extracted data. This extracted ...
Howard D. Wactlar, Alexander G. Hauptmann, Michael...
CIKM
2011
Springer
12 years 6 months ago
Citation count prediction: learning to estimate future citations for literature
In most of the cases, scientists depend on previous literature which is relevant to their research fields for developing new ideas. However, it is not wise, nor possible, to trac...
Rui Yan, Jie Tang, Xiaobing Liu, Dongdong Shan, Xi...
ECCV
2008
Springer
14 years 8 months ago
FaceTracer: A Search Engine for Large Collections of Images with Faces
We have created the first image search engine based entirely on faces. Using simple text queries such as "smiling men with blond hair and mustaches," users can search thr...
Neeraj Kumar, Peter N. Belhumeur, Shree K. Nayar