Tinne Tuytelaars

Learn More
We demonstrate the performance of our interest point detector/descriptor scheme SURF – Speeded Up Robust Features – in an application that finds correspondences to a reference image in realtime. The user takes a reference image with a handheld video camera and then moves the camera around the object. The system identifies interest points in every newly(More)
This article presents a novel scaleand rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features). SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image(More)
The paper gives 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. Six types of detectors are included: detectors based on affine normalization around Harris  (Mikolajczyk and  Schmid, 2002; Schaffalitzky and  Zisserman, 2002) and Hessian points (More)
In this paper, we introduce a new domain adaptation (DA) algorithm where the source and target domains are represented by subspaces described by eigenvectors. In this context, our method seeks a domain adaptation solution by learning a mapping function which aligns the source subspace with the target one. We show that the solution of the corresponding(More)
Over the years, several spatio-temporal interest point detectors have been proposed. While some detectors can only extract a sparse set of scaleinvariant features, others allow for the detection of a larger amount of features at user-defined scales. This paper presents for the first time spatio-temporal interest points that are at the same time(More)
‘Invariant regions’ are self-adaptive image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions can be extracted directly from a single image. They are then described by a set of invariant features, which makes it relatively easy to match them between views, even under wide(More)
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to three open questions:(l) whether the invariant local features are suitable for scene (rather than object) classification; (2) whether unsupennsed latent space models can be used(More)
‘Invariant regions’ are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then described by a set of invariant features, which makes it relatively easy to match them between views and under changing illumination. In previous work, we have presented invariant regions(More)
In this paper we present a method to capture video-wide temporal information for action recognition. We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution of the appearance within the video. We learn such ranking functions per video via a ranking machine and use the parameters(More)