On the Selection of Verbs for Natural Language Description of Traffic Scenes
GWAI '82 Proceedings of the 6th German Workshop on Artificial Intelligence
Natural language dialogue about moving objects in an automatically analyzed traffic scene
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 1
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Generating a coherent text describing a traffic scene
COLING '86 Proceedings of the 11th coference on Computational linguistics
Pattern Recognition Letters
Knowledge and Event-Based System for Video-Surveillance Tasks
IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part I: Methods and Models in Artificial and Natural Computation. A Homage to Professor Mira's Scientific Legacy
A task-driven intelligent workspace system to provide guidance feedback
Computer Vision and Image Understanding
Spatial knowledge representation for human-robot interaction
Spatial cognition III
Logical formalization of multimedia interpretation
Knowledge-driven multimedia information extraction and ontology evolution
Hi-index | 0.00 |
For an adequate interpretation of image sequences it is not only necessary to recognize objects and object positions but also certain interesting temporal developments of the scene, called events. In this paper we discuss event models for traffic scenes as high-level conceptual structures which permit interfacing to an existing natural language dialogue system. Event models are declarative descriptions of classes of events organized around verbs of locomotion. They involve components which are directly related to the deep case structure of a corresponding natural language description. Event models may be used for bottom-up scene description as well as top-down question-answering. They may also incorporate expectations about a scene, thus providing an interface to experience and common sense.