Sciweavers

791 search results - page 77 / 159
» A structure from motion inequality
Sort
View
104
Voted
AI
2005
Springer
15 years 28 days ago
Learning to talk about events from narrated video in a construction grammar framework
The current research presents a system that learns to understand object names, spatial relation terms and event descriptions from observing narrated action sequences. The system e...
Peter Ford Dominey, Jean-David Boucher
ICPR
2000
IEEE
16 years 2 months ago
Estimation of the Location of Joint Points of Human Body from Successive Volume Data
Recognizing structure of human body is important for modeling human motion. Human body is usually represented as an articulate model, which consists of the rigid parts and the joi...
Masaaki Iiyama, Yoshinari Kameda, Michihiko Minoh
120
Voted
ICMCS
1999
IEEE
117views Multimedia» more  ICMCS 1999»
15 years 5 months ago
VHS to VRML: 3D Graphical Models from Video Sequences
Abstract-- We describe a method to completely automatically recover 3D scene structure together with a camera for each frame from a sequence of images acquired by an unknown camera...
Andrew Zisserman, Andrew W. Fitzgibbon, Geoffrey C...
CVPR
2012
IEEE
13 years 3 months ago
Nonparametric discovery of activity patterns from video collections
We propose a nonparametric framework based on the beta process for discovering temporal patterns within a heterogenous video collection. Starting from quantized local motion descr...
Michael C. Hughes, Erik B. Sudderth
IJRR
2007
236views more  IJRR 2007»
15 years 28 days ago
Towards High-resolution Imaging from Underwater Vehicles
Large area mapping at high resolution underwater continues to be constrained by sensor-level environmental constraints and the mismatch between available navigation and sensor acc...
Hanumant Singh, Christopher N. Roman, Oscar Pizarr...