BING: Binarized normed gradients for objectness estimation at 300fps
- Submitting institution
-
University of Oxford
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9516
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2014.414
- Title of conference / published proceedings
- Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- First page
- 3286
- Volume
- -
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Out of scope for open access requirements
- Month of publication
- September
- Year of publication
- 2015
- 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)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- As one of the most important areas in computer vision, object detection has made great strides in recent years. However, most state-of-the-art detectors still require each category specific classifiers to evaluate many image windows in a sliding window fashion. In this paper, we propose a surprisingly simple and powerful feature "BING" to help the search for objects using objectness scores. This work later inspired a large corpus of work on similar objectness criteria and attracted funding from Huawei (GBP450,000) to continue working on image enhancement for phones.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -