Pairwise Decomposition of Image Sequences for Active Multi-View Recognition
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2420
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2016.414
- Title of conference / published proceedings
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- First page
- 3813
- Volume
- 2016-December
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
10.1109/CVPR.2016.414
- 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
- 78
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- First work to achieve image-based object recognition over arbitrary camera trajectories with a machine learning approach, when previously this required full 3D reconstructions. Significantly outperforms these traditional approaches and, at the time of publication, was the state-of-the-art on the standard multi-view object recognition benchmark, Princeton ModelNet (http://modelnet.cs.princeton.edu). Incorporated into a number of computer vision undergraduate courses and international tutorials, e.g. University of Texas (http://vision.cs.utexas.edu/381V-fall2016) and KAIST (http://multispectral.kaist.ac.kr/iskweon/RSS2016_LectureNote.pdf). CVPR 2016 oral presentation acceptance rate: 2.7%/2680 submissions.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
