Deep Filter Banks for Texture Recognition, Description, and Segmentation
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14187
- Type
- D - Journal article
- DOI
-
10.1007/s11263-015-0872-3
- Title of journal
- International Journal of Computer Vision
- Article number
- 1
- First page
- 65
- Volume
- 118
- Issue
- 1
- ISSN
- 0920-5691
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2016
- 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
-
3
- Research group(s)
-
-
- Citation count
- 146
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work stratified the elusive problem of texture analysis by introducing a novel dataset of human-interpretable texture attributes and establishing state-of-the-art systems for texture classification and segmentation. This work has now become the standard starting point for texture understanding, and serves as the standard benchmark by which methods are compared by the entire texture analysis community. The fine-grained analysis of texture we introduced has facilitated applications such as texture-controllable garment and fashion synthesis in Facebook’s efforts on creative AI.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -