Recurrent Confabulation Model for Annotated Image Retrieval
| Autor: | Ryo Izawa, Naoki Motohashi, Tomohiro Takagi |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Information retrieval
Computer science business.industry computer.software_genre Theoretical Computer Science Human-Computer Interaction Artificial Intelligence medicine Visual Word Artificial intelligence medicine.symptom Confabulation (neural networks) business Image retrieval computer Software Word (computer architecture) Brain function Natural language processing |
| Zdroj: | International Journal of Intelligent Systems. 28:37-51 |
| ISSN: | 0884-8173 |
| DOI: | 10.1002/int.21573 |
| Popis: | A text-based image retrieval system based on a brain function model, called the combination confabulation model, was developed to recognize how contextual word meanings change depending on the situation to overcome semantic gaps. In addition, a recurrent version of this system was developed to improve retrieval accuracy. The system uses a casebase that contains matched pairs of descriptions and images and searches for images that match the input queries. Experimental results showed that the proposed system exhibited more accurate image retrieval performances than conventional systems. © 2013 Wiley Periodicals, Inc. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|