Event Models for Recognition and Natural Language Description of Events in Real-World Image Sequences
Explore this paper's citation graph
Summary
This paper discusses event models for traffic scenes as high-level conceptual structures which permit interfacing to an existing natural language dialogue system.
- Type
- article
- Published
- 1983-08-01
- Cited by
- 73
- References
- 11
- OpenAlex
- https://openalex.org/W126560389
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11838582
Keywords
Computer science, Event (particle physics), Interfacing, Natural language processing, Natural language
References
- Natural Language Dialogue about Moving Objects in an Automatically Analyzed Traffic Scene
- Representation of Time and Sequences of Events
- Towards Natural Language Description of Real-World Image Sequences
- Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene
- Temporal scene analysis: conceptual descriptions of object movements.
- Language and Perception
- A framework for visual motion understanding
- Glancing, Referring and Explaining in the Dialogue System HAM-RPM
- On the Selection of Verbs for Natural Language Description of Traffic Scenes
Cited by
- Dynamic Scene Description System – ODYS
- Division of Work During Behaviour Recognition - The SCENIC Approach
- Activity Representation Using 3D Shape Models
- Qualitative Reasoning for Automated Traffic Surveillance
- Natural Language Sourcebook.
- Generation of qualitative spatio-temporal representations from visual input
- Multi-modal scene understanding using probabilistic models
- Bibliography of Research in Natural Language Generation
- 1st order C-cubes for the interpretation of Petri nets: an application to dynamic scene understanding
- Combining visual recognition and computational linguistics : linguistic knowledge for visual recognition and natural language descriptions of visual content
- Knowledge Structure In Object Recognition
- From imagery to salience: locative expressions in context
- Bridging the gap between modal temporal logics and constraint-based QSR as an ALC(D) spatio-temporalisation with weakly cyclic TBoxes
- Knowledge-Driven Multimedia Information Extraction and Ontology Evolution - Bridging the Semantic Gap
- Spatial Models for Wide-Area Visual Surveillance: Computational Approaches and Spatial Building-Blocks
- From image sequences towards conceptual descriptions
- Multi‐agent system for knowledge‐based event recognition and composition
- Reconstructing force-dynamic models from video sequences
- The Computational Perception of Scene Dynamics
- Understanding object motion: Recognition, learning and spatiotemporal reasoning
Related papers
- Language and Perception
- Generating and Understanding Scene Descriptions.
- Natural Language Access to Visual Data: Dealing with Space and Movement
- Over-Answering Yes-No Questions: Extended Responses in a NL Interface to a Vision System
- Scene knowledge representation for expert vision systems
- Steps toward a Cognitive Vision System
- Learning Spatial Knowledge for Text to 3D Scene Generation