K
Krystian Mikolajczyk
Researcher at Imperial College London
Publications - 157
Citations - 35527
Krystian Mikolajczyk is an academic researcher from Imperial College London. The author has contributed to research in topics: Image retrieval & Feature extraction. The author has an hindex of 47, co-authored 144 publications receiving 33081 citations. Previous affiliations of Krystian Mikolajczyk include Facebook & Czech Technical University in Prague.
Papers
More filters
Journal ArticleDOI
A performance evaluation of local descriptors
TL;DR: It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Journal ArticleDOI
Scale & Affine Invariant Interest Point Detectors
TL;DR: A comparative evaluation of different detectors is presented and it is shown that the proposed approach for detecting interest points invariant to scale and affine transformations provides better results than existing methods.
Proceedings ArticleDOI
A performance evaluation of local descriptors
TL;DR: It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Journal ArticleDOI
A Comparison of Affine Region Detectors
Krystian Mikolajczyk,Tinne Tuytelaars,Cordelia Schmid,Andrew Zisserman,Jiri Matas,Frederik Schaffalitzky,Timor Kadir,L. Van Gool +7 more
TL;DR: 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.
Journal ArticleDOI
Tracking-Learning-Detection
TL;DR: A novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection, and develops a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: P-expert estimates missed detections, and N-ex Expert estimates false alarms.