C
Christian Leistner
Researcher at Microsoft
Publications - 55
Citations - 5695
Christian Leistner is an academic researcher from Microsoft. The author has contributed to research in topics: Boosting (machine learning) & Random forest. The author has an hindex of 26, co-authored 55 publications receiving 5367 citations. Previous affiliations of Christian Leistner include ETH Zurich & Graz University of Technology.
Papers
More filters
Book ChapterDOI
Semi-supervised On-Line Boosting for Robust Tracking
TL;DR: The main idea is to formulate the update process in a semi-supervised fashion as combined decision of a given prior and an on-line classifier, without any parameter tuning, which significantly alleviates the drifting problem in tracking applications.
Proceedings ArticleDOI
Fast and accurate image upscaling with super-resolution forests
TL;DR: This paper shows the close relation of previous work on single image super-resolution to locally linear regression and demonstrates how random forests nicely fit into this framework, and proposes to directly map from low to high-resolution patches using random forests.
Proceedings ArticleDOI
On-line Random Forests
TL;DR: A novel on-line random forest algorithm is proposed that combines ideas from on-lines bagging, extremely randomized forests and propose an on- line decision tree growing procedure and adds a temporal weighting scheme for adaptively discarding some trees based on their out-of-bag-error in given time intervals and consequently growing of new trees.
Proceedings ArticleDOI
Learning object class detectors from weakly annotated video
TL;DR: It is shown that training from a combination of weakly annotated videos and fully annotated still images using domain adaptation improves the performance of a detector trained from still images alone.
Proceedings ArticleDOI
PROST: Parallel robust online simple tracking
TL;DR: This work shows that augmenting an on-line learning method with complementary tracking approaches can lead to more stable results, and uses a simple template model as a non-adaptive and thus stable component, a novel optical-flow-based mean-shift tracker as highly adaptive element and anon-line random forest as moderately adaptive appearance-based learner.