Distinction of 3D Objects and Scenes via
Classification Network and Markov Random Field
- Submitting institution
-
Edge Hill University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 20350787
- Type
- D - Journal article
- DOI
-
10.1109/TVCG.2018.2885750
- Title of journal
- IEEE Transactions on Visualization and Computer Graphics
- Article number
- 8567954
- 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
- The proposed method has attracted at least 4 citations (google scholar) since its publication in June 2020 and has been selected for a comparative study in ACM Transactions on Graphics, 39(2020) 158: 1-14. It has also been further developed for improved performance in IEEE Transactions on Visualization and Computer Graphics, 27(2021) 151–164 and for salient view selection of 3D objects and scenes in Proceedings of ECCV, 2020, pp. 454-470. It has successfully addressed the challenging issue in the acquisition of ground truth pixel level saliency data for training and thus has an advantage of easy implementation.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -