Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
This paper introduces a new visual representation of a document or group of documents, a Dynamic Document Icon, or Dydocon. Its representation is symbolic like an icon, but change...
This paper presents a novel Gaussianized vector representation for scene images by an unsupervised approach. First, each image is encoded as an ensemble of orderless bag of featur...
Hao Tang, Mark Hasegawa-Johnson, Thomas S. Huang, ...
We extend the constellation model to include heterogeneous parts which may represent either the appearance or the geometry of a region of the object. The parts and their spatial co...
Statistical approaches for building non-rigid deformable
models, such as the Active Appearance Model (AAM), have
enjoyed great popularity in recent years, but typically require
...
Akshay Asthana (Australian National University), R...