Learning to Generate Descriptions of Visual Data Anchored in Spatial Relations
- Submitting institution
-
University of Brighton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7139259
- Type
- D - Journal article
- DOI
-
10.1109/MCI.2017.2708559
- Title of journal
- IEEE Computational Intelligence Magazine
- Article number
- -
- First page
- 29
- Volume
- 12
- Issue
- 3
- ISSN
- 1556-603X
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Determining and describing how entities are positioned in relation to each other in a 2D image is a notoriously difficult task. This paper is significant because it introduces a new end-to-end methodology, using selected geometric and linguistic features to characterise spatial relations. The determination of the spatial relations between entities in an image has implications for the expanding proportion of the population who are visually impaired.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -