MLCVNet: multi-level context VoteNet for 3D object detection
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 104749438
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR42600.2020.01046
- Title of conference / published proceedings
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- First page
- 10444
- Volume
- 0
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2020
- URL
-
https://doi.org/10.1109/CVPR42600.2020.01046
- 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
-
6
- Research group(s)
-
V - Visual computing
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes capturing and integrating multi-level contextual information, including points, objects and scenes, for 3D object detection, which is an essential task for machine perception with many real-world applications. It outperforms existing techniques on benchmark datasets. The method is described as “state of the art” by other researchers (https://openaccess.thecvf.com/content/WACV2021/html/Yang_SliceNets_--_A_Scalable_Approach_for_Object_Detection_in_3D_WACV_2021_paper.html). The paper was presented at CVPR 2020, and the code is available online (https://github.com/NUAAXQ/MLCVNet).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -