Center for Vision, Cognition, Learning, and Art (VCLA)

The Center for Vision, Cognition, Learning, and Art (VCLA) is affiliated with the Departments of Statistics and Computer Science at UCLA. We start from Computer Vision and expand to other disciplines.

Our projects span four directions:

Vision: object, scene, events, inference strategies, and sensor control;
Cognition: intentions, roles, goals, causality, affordance and persuasion;
Learning: information projection, stochastic grammars, and goal guided learning;
Art: abstraction, expression, aesthetics, freedom, and perceptual entropy.

Our objective is to pursue a unified framework for representation, learning, inference and reasoning, and to build intelligent computer systems for real world applications.

Our projects have been supported by NSF,ONR, DARPA, Keck Foundation, Sloan Foundation, Microsoft, Kodak, and Siemens.

Learning Mixed Image Templates for Object Recognition	From Image Parsing to Painterly Rendering	A Hierarchical and Contextual Model for Aerial Image Parsing

This project explores both local structure and local texture features in learning image templates, which are maximum likelihood representations of observed images from specified object categories...	We present a semantics-driven approach for stroke-based painterly rendering, based on recent image parsing techniques in computer vision. Image parsing integrates segmentation for regions,...	We present a hierarchical and contextual model for aerial image understanding. Our model organizes objects (cars, roofs, roads, trees, parking lots) in aerial scenes into hierarchical...

Learning Mixed Image Templates for Object Recognition

From Image Parsing to Painterly Rendering

A Hierarchical and Contextual Model for Aerial Image Parsing