324 search results - page 30 / 65 » Learning Semantic Scene Models by Trajectory Analysis |
CVPR
2011
IEEE
14 years 5 months ago
2011
IEEE
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....
111
click to vote
JMLR
2006
14 years 9 months ago
2006
We develop a new component analysis framework, the Noisy-Or Component Analyzer (NOCA), that targets high-dimensional binary data. NOCA is a probabilistic latent variable model tha...
ICCV
2007
IEEE
15 years 11 months ago
2007
IEEE
Occlusion is a significant challenge for many tracking algorithms. Most current methods can track through transient occlusion, but cannot handle significant extended occlusion whe...
91
Voted
MM
2009
ACM
15 years 4 months ago
2009
ACM
In this paper, we exploit the problem of inferring images’ semantic concepts from community-contributed images and their associated noisy tags. To infer the concepts more accura...
91
Voted
MM
2009
ACM
15 years 4 months ago
2009
ACM
The main difficulty in face image modeling is to decompose those semantic factors contributing to the formation of the face images, such as identity, illumination and pose. One p...