| Objectives |
|
The aim of this work-package is to prepare numerical visual data to knowledge extraction and multimodality semantics association. Tasks will focus on visual content indexing and mining (still images and video). There is a progression from low-level, mid-level to high-level analysis. Tasks should get outputs from and work closely with Machine Learning and Benchmarking work-packages, and provide necessary inputs for other work-packages, mainly Cross-Modal Integration and Benchmarking. We aim to:
|