Sciweavers

5516 search results - page 970 / 1104
» A Topological Approach to Recognition
Sort
View
IROS
2006
IEEE
247views Robotics» more  IROS 2006»
16 years 12 days ago
Towards Open-Ended 3D Rotation and Shift Invariant Object Detection for Robot Companions
- Robot companions need to be able to constantly acquire knowledge about new objects for instance in order to detect them in the environment. This ability is necessary since it is ...
Jens Kubacki, Winfried Baum
ISCAS
2006
IEEE
96views Hardware» more  ISCAS 2006»
16 years 12 days ago
On the initialization of the DNMF algorithm
— A subspace supervised learning algorithm named Discriminant Non-negative Matrix Factorization (DNMF) has been recently proposed for classifying human facial expressions. It dec...
Ioan Buciu, Nikos Nikolaidis, Ioannis Pitas
MIR
2006
ACM
141views Multimedia» more  MIR 2006»
16 years 10 days ago
Mining temporal patterns of movement for video content classification
Scalable approaches to video content classification are limited by an inability to automatically generate representations of events ode abstract temporal structure. This paper pre...
Michael Fleischman, Philip DeCamp, Deb Roy
MIR
2006
ACM
189views Multimedia» more  MIR 2006»
16 years 10 days ago
Dynamic storyboards for video content summarization
We propose an innovative, general purpose, approach to the selection and hierarchical representation of key frames of a video sequence for video summarization. In the first stage ...
Gianluigi Ciocca, Raimondo Schettini
MM
2006
ACM
175views Multimedia» more  MM 2006»
16 years 10 days ago
Real-time automatic 3D scene generation from natural language voice and text descriptions
Automatic scene generation using voice and text offers a unique multimedia approach to classic storytelling and human computer interaction with 3D graphics. In this paper, we pre...
Lee M. Seversky, Lijun Yin