• Learning, analysis, and detection of motion in the framework of a hierarchical compositional visual architecture
The Client : Javna agencija za raziskovalno dejavnost RS
Project type: Research projects ARRS
Project duration: 2011 - 2014
  • Description

The proposed project aims at a holistic approach towards learning, detection and recognition / categorisation of visual motion and phenomena derived from it. The approach is based on a novel and powerful paradigm of learning multi-layer compositional herarchies. While individual ingredients, such as hierarchical processing, compositionality and incremental learning, have already been subjects of a motion-related framework. Such a framework is crucial for robustness, versatility, ease of learning and inference, generalisation, real-time performance, transfer of the knowledge and scalability for a variety of cognitive vision tasks.