M
Michael Felsberg
Researcher at Linköping University
Publications - 272
Citations - 26863
Michael Felsberg is an academic researcher from Linköping University. The author has contributed to research in topics: Video tracking & Computer science. The author has an hindex of 47, co-authored 248 publications receiving 21131 citations. Previous affiliations of Michael Felsberg include ETH Zurich & University of Kiel.
Papers
More filters
Proceedings ArticleDOI
Accurate scale estimation for robust visual tracking
TL;DR: This paper presents a novel approach to robust scale estimation that can handle large scale variations in complex image sequences and shows promising results in terms of accuracy and efficiency.
Proceedings ArticleDOI
ECO: Efficient Convolution Operators for Tracking
TL;DR: This work revisit the core DCF formulation and introduces a factorized convolution operator, which drastically reduces the number of parameters in the model, and a compact generative model of the training sample distribution that significantly reduces memory and time complexity, while providing better diversity of samples.
Proceedings ArticleDOI
Learning Spatially Regularized Correlation Filters for Visual Tracking
TL;DR: The proposed SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples, and an optimization strategy is proposed, based on the iterative Gauss-Seidel method, for efficient online learning.
Proceedings ArticleDOI
Adaptive Color Attributes for Real-Time Visual Tracking
TL;DR: The contribution of color in a tracking-by-detection framework is investigated and an adaptive low-dimensional variant of color attributes is proposed, suggesting that color attributes provides superior performance for visual tracking.
Book ChapterDOI
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
TL;DR: Discriminative Correlation Filters have demonstrated excellent performance for visual object tracking and the key to their success is the ability to efficiently exploit available negative data.