Skip to search formSkip to main contentSkip to account menu
Robust Wide Baseline Stereo from Maximally Stable Extremal Regions
TLDR
The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints, is studied and an efficient and practically fast detection algorithm is presented for an affinely-invariant stable subset of extremal regions, the maximally stable extremal region (MSER).
View via Publisher
A Comparison of Affine Region Detectors
TLDR
A snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions to establish a reference test set of images and performance software so that future detectors can be evaluated in the same framework.
View on Springer
Combining classifiers
We develop a common theoretical framework for combining classifiers which use distinct pattern representations and show that many existing schemes can be considered as special cases of compound…
View on IEEE
ICDAR 2015 competition on Robust Reading
TLDR
A new Challenge 4 on Incidental Scene Text has been added to the Challenges on Born-Digital Images, Focused Scene Images and Video Text and tasks assessing End-to-End system performance have been introduced to all Challenges.
View on IEEE
The Visual Object Tracking VOT2016 Challenge Results
TLDR
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
View via Publisher
P-N learning: Bootstrapping binary classifiers by structural constraints
TLDR
It is shown that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, and a theory that formulates the conditions under which P-N learning guarantees improvement of the initial classifier is proposed and validated on synthetic and real data.
View on IEEE
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
TLDR
DeblurGAN achieves state-of-the art performance both in the structural similarity measure and visual appearance and is 5 times faster than the closest competitor - Deep-Deblur.
View on IEEE
XM2VTSDB: The Extended M2VTS Database
TLDR
This poster presents a poster presenting a probabilistic procedure for estimating the response of the immune system to laser-spot assisted surgery to treat central giant cell granuloma.
Matching with PROSAC - progressive sample consensus
  • O. Chum, Jiri Matas
  • Computer Science
    IEEE Computer Society Conference on Computer…
  • 20 June 2005
TLDR
A new robust matching method, PROSAC, which exploits the linear ordering defined on the set of correspondences by a similarity function used in establishing tentative correspondences and achieves large computational savings.
View on IEEE
The Visual Object Tracking VOT2015 Challenge Results
TLDR
The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and presents a new VOT 2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License