R
Rui Caseiro
Researcher at University of Coimbra
Publications - 31
Citations - 8461
Rui Caseiro is an academic researcher from University of Coimbra. The author has contributed to research in topics: Point distribution model & Bayesian inference. The author has an hindex of 16, co-authored 31 publications receiving 6940 citations.
Papers
More filters
Journal ArticleDOI
High-Speed Tracking with Kernelized Correlation Filters
TL;DR: A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.
Book ChapterDOI
Exploiting the circulant structure of tracking-by-detection with kernels
TL;DR: Using the well-established theory of Circulant matrices, this work provides a link to Fourier analysis that opens up the possibility of extremely fast learning and detection with the Fast Fourier Transform, which can be done in the dual space of kernel machines as fast as with linear classifiers.
Book ChapterDOI
Semantic segmentation with second-order pooling
TL;DR: This paper introduces multiplicative second-order analogues of average and max-pooling that together with appropriate non-linearities lead to state-of-the-art performance on free-form region recognition, without any type of feature coding.
Proceedings ArticleDOI
Globally optimal solution to multi-object tracking with merged measurements
TL;DR: A new graph structure is presented that encodes multiple-match events as standard one-to-one matches, allowing computation of the solution in polynomial time, and an efficient method to identify groups is also presented, as a flow circulation problem.
Proceedings ArticleDOI
Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition
TL;DR: This paper derives a transformation based on the Fourier transform that block-diagonalizes the Gram matrix, at once eliminating redundancies and partitioning the learning problem, and allows training with all the potential samples in sets of thousands of images.