output
20022018
most citedBeyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking

1.8k citations

Showing cs.CVShow all

10 papers · 1 filter

cs.CV2017617 cited

HDR image reconstruction from a single exposure using deep CNNs

Gabriel Eilertsen, Joel Kronander, Gyorgy Denes +2

Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combi…

cs.CV201738 cited

Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications

Apostolia Tsirikoglou, Joel Kronander, Magnus Wrenninge +1

We present an overview and evaluation of a new, systematic approach for generation of highly realistic, annotated synthetic data for training of deep neural networks in computer vi…

cs.CV201717 cited

Deep Projective 3D Semantic Segmentation

Felix Järemo Lawin, Martin Danelljan, Patrik Tosteberg +3

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmenta…

cs.CV20169 cited

Deep Motion Features for Visual Tracking

Susanna Gladh, Martin Danelljan, Fahad Shahbaz Khan +1

Robust visual tracking is a challenging computer vision problem, with many real-world applications. Most existing approaches employ hand-crafted appearance features, such as HOG or…

cs.CV20163 cited

Discriminative Scale Space Tracking

Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan +1

Accurate scale estimation of a target is a challenging research problem in visual object tracking. Most state-of-the-art methods employ an exhaustive scale search to estimate the t…

cs.CV201636 cited

Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking

Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan +1

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set.…