Sciweavers

7518 search results - page 1331 / 1504
» From images to 3D models
Sort
View
CVPR
2011
IEEE
15 years 1 months ago
What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
Brian Kulis, Kate Saenko, Trevor Darrell
ICMCS
2006
IEEE
106views Multimedia» more  ICMCS 2006»
16 years 17 days ago
Scalability in Human Shape Analysis
This paper proposes a new approach for the human motion analysis. The main contribution comes from the proposed representation of the human body. Most of already existing systems ...
Thomas Fourès, Philippe Joly
CVPR
2007
IEEE
16 years 8 months ago
Accurate, Dense, and Robust Multi-View Stereopsis
: This paper proposes a novel algorithm for calibrated multi-view stereopsis that outputs a (quasi) dense set of rectangular patches covering the surfaces visible in the input imag...
Yasutaka Furukawa, Jean Ponce
ECCV
2008
Springer
16 years 8 months ago
Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
Abhinav Gupta, Larry S. Davis
ICIP
2006
IEEE
16 years 8 months ago
Practical Wyner-Ziv Switching Scheme for Multiple Bit-Rate Video Streaming
In this paper, we propose a novel bit-stream switching scheme for the multiple bit-rate (MBR) video streaming, in which a Wyner-Ziv coded frame is used to overcome the mismatch be...
Mei Guo, Yan Lu, Feng Wu, Debin Zhao, Wen Gao
« Prev « First page 1331 / 1504 Last » Next »