The central goal of iV&L Net is to build a European CV/NLP research community, targeting four focus themes:
- Integrated Modelling of Vision and Language for CV and NLP Tasks;
- Applications of Integrated Models;
- Automatic Generation of Image & Video Descriptions; and
- Semantic Image & Video Search.
iV&L Net will organise annual conferences, technical meetings, partner visits, data/task benchmarking, and industry/end-user liaison.