Sciweavers

844 search results - page 59 / 169
» From Motion Observation to Qualitative Motion Representation
Sort
View
ICASSP
2010
IEEE
13 years 9 months ago
Synthesizing speech from Doppler signals
It has long been considered a desirable goal to be able to construct an intelligible speech signal merely by observing the talker in the act of speaking. Past methods at performin...
Arthur R. Toth, Kaustubh Kalgaonkar, Bhiksha Raj, ...
CVPR
2008
IEEE
14 years 11 months ago
View-invariant recognition of body pose from space-time templates
We propose a new template-based approach for viewinvariant recognition of body poses, based on geometric constraints derived from the motion of body point triplets. In addition to...
Yuping Shen, Hassan Foroosh
CVIU
2008
192views more  CVIU 2008»
13 years 9 months ago
Content based video matching using spatiotemporal volumes
This paper presents a novel framework for matching video sequences using the spatiotemporal segmentation of videos. Instead of using appearance features for region correspondence ...
Arslan Basharat, Yun Zhai, Mubarak Shah
ICCV
2003
IEEE
14 years 11 months ago
Video Input Driven Animation (VIDA)
There are many challenges associated with the integration of synthetic and real imagery. One particularly difficult problem is the automatic extraction of salient parameters of na...
Meng Sun, Allan D. Jepson, Eugene Fiume
CVPR
2007
IEEE
14 years 11 months ago
Segmenting Motions of Different Types by Unsupervised Manifold Clustering
We propose a novel algorithm for segmenting multiple motions of different types from point correspondences in multiple affine or perspective views. Since point trajectories associ...
Alvina Goh, René Vidal