-
Chapter and Conference Paper
ERA: Enhanced Rational Activations
Activation functions play a central role in deep learning since they form an essential building stone of neural networks. In the last few years, the focus has been shifting towards investigating new types of a...
-
Article
Fixed-Lens camera setup and calibrated image registration for multifocus multiview 3D reconstruction
Image-based 3D reconstruction or 3D photogrammetry of small-scale objects including insects and biological specimens is challenging due to the use of a high magnification lens with inherently limited depth of ...
-
Article
Correction to: The practice of emergency radiology throughout Europe: a survey from the European Society of Emergency Radiology on volume, staffing, equipment, and scheduling
A Correction to this paper has been published: https://doi.org/10.1007/s00330-020-07520-2
-
Article
The practice of emergency radiology throughout Europe: a survey from the European Society of Emergency Radiology on volume, staffing, equipment, and scheduling
To obtain information from radiology departments throughout Europe regarding the practice of emergency radiology
-
Chapter and Conference Paper
Fast and Differentiable Message Passing on Pairwise Markov Random Fields
Despite the availability of many Markov Random Field (MRF) optimization algorithms, their widespread usage is currently limited due to imperfect MRF modelling arising from hand-crafted model parameters and the...
-
Reference Work Entry In depth
Projective Reconstruction
-
Article
Hallucinating Unaligned Face Images by Multiscale Transformative Discriminative Networks
Conventional face hallucination methods heavily rely on accurate alignment of low-resolution (LR) faces before upsampling them. Misalignment often leads to deficient results and unnatural artifacts for large u...
-
Chapter and Conference Paper
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We study the problem of learning l...
-
Living Reference Work Entry In depth
Stereovision
-
Article
Identity-Preserving Face Recovery from Stylized Portraits
Given an artistic portrait, recovering the latent photorealistic face that preserves the subject’s identity is challenging because the facial details are often distorted or fully lost in artistic portraits. We...
-
Chapter and Conference Paper
Scalable Deep k-Subspace Clustering
Subspace clustering algorithms are notorious for their scalability issues because building and processing large affinity matrices are demanding. In this paper, we introduce a method that simultaneously learns ...
-
Article
Open AccessDevelopment of a 3D workspace shoulder assessment tool incorporating electromyography and an inertial measurement unit—a preliminary study
Traditional shoulder range of movement (ROM) measurement tools suffer from inaccuracy or from long experimental setup times. Recently, it has been demonstrated that relatively low-cost wearable inertial measur...
-
Chapter and Conference Paper
Face Super-Resolution Guided by Facial Component Heatmaps
State-of-the-art face super-resolution methods leverage deep convolutional neural networks to learn a map** between low-resolution (LR) facial patterns and their corresponding high-resolution (HR) counterpar...
-
Chapter and Conference Paper
Action Anticipation with RBF Kernelized Feature Map** RNN
We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called feature map** RNN. Our novel RNN architecture builds upon three effective prin...
-
Chapter
Dictionary Learning on Grassmann Manifolds
Sparse representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models...
-
Chapter
Kernels on Riemannian Manifolds
We discuss an approach to exploiting kernel methods with manifold-valued data. In many computer vision problems, the data can be naturally represented as points on a Riemannian manifold. Due to the non-Euclide...
-
Article
A Generalized Projective Reconstruction Theorem and Depth Constraints for Projective Factorization
This paper presents a generalized version of the classic projective reconstruction theorem which helps to choose or assess depth constraints for projective depth estimation algorithms. The theorem shows that p...
-
Article
Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds
Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features an...
-
Article
\({L_q}\) -Closest-Point to Affine Subspaces Using the Generalized Weiszfeld Algorithm
This paper presents a method for finding an \(L_q\) ...
-
Chapter and Conference Paper
Reliable Point Correspondences in Scenes Dominated by Highly Reflective and Largely Homogeneous Surfaces
Common Structure from Motion (SfM) tasks require reliable point correspondences in images taken from different views to subsequently estimate model parameters which describe the 3D scene geometry. For example ...
