Integrating Vision and Language: Towards Automatic Description of Human Movements

摘要: The integration of vision and natural language processing increasingly attracts attention in different areas AI research. Up to now, however, there have only been a few attempts at connecting systems with access systems. Within the SFB 314, special collaborative program on knowledge-based systems, automatic description real world image sequences constitutes major research goal, which has pursued during last ten years. aim our approach is obtain an incremental evaluation simultaneous perceived time-varying scenes. In this contribution we will report new results joint efforts combining system Vitra system. We investigated problem describing movements articulated bodies within integrated computer paper focus model-based for recognition pedestrians further production Vitra.