Distinction of 3D Objects and Scenes via Classification Network and Markov Random Field
- Submitting institution
-
University of Brighton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7149433
- Type
- D - Journal article
- DOI
-
10.1109/TVCG.2018.2885750
- Title of journal
- IEEE Transactions on Visualization and Computer Graphics
- Article number
- -
- First page
- 2204
- Volume
- 26
- Issue
- 6
- ISSN
- 1077-2626
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2018
- 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
-
2
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Automatically detecting what an image or 3D object represents, and hence classifying it by finding similarities (and dissimilarities) to other objects in the same collection, require the computer to emulate tasks made by humans, such as detecting distinctive areas. This paper is significant because it proposes a method which does not require predefined handcrafted features, yet behaves consistently with human perception. The results are used as one of two key comparators for Unsupervised Detection of Distinctive Regions on 3D Shapes (Li et al., ACM Transactions on Graphics, 2020).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -