Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation
We present a solution for Accurate and temporally consistent modeling of human performances from video sequences. In detail, we derive parameters of a sequence of body models, representing shape and motion of a person, including jaw poses, facial...
From Explanations to Segmentation: Using Explainable AI for Image Segmentation
The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on pixel-precision. In...
Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects
We present a multi-object 6D detection and tracking pipeline for potentially similar and non-textured objects. The combination of a convolutional neural network for object classification and rough pose estimation with a local pose refinement and...
Overview of the Neural Network Compression and Representation (NNR) Standard
Neural Network Coding and Representation (NNR) is the first international standard for efficient compression of neural networks. The NNR standard contains quantization and an arithmetic coding scheme as core encoding and decoding technologies, as...
Automated Damage Inspection of Power Transmission Towers from UAV Images
This paper adresses the problem of structural damage detection in transmission towers, addressing these two common challenges: (i) the lack of freely available training data and the difficulty to collect it; (ii) fuzzy boundaries of what...
Continuous wave terahertz receivers with 4.5 THz bandwidth and 112 dB dynamic range
We present photomixers made of InGaAs:Fe as broadband receivers in optoelectronic cw THz systems. The improved resistivity and carrier lifetime of InGaAs:Fe enable us to measure a bandwidth of 4.5 THz with a peak dynamic range of 112 dB. When...
ML-assisted QoT estimation: a dataset collection and data visualization for dataset quality evaluation
We present a publicly available dataset collection to open the problem of data-driven QoT estimation to the ML community. The dataset collection allows comparing various solutions presented by different research groups. Furthermore, we propose...
Explaining Machine Learning Models for Clinical Gait Analysis
This article investigates the usefulness of Explainable Artificial Intelligence (XAI) methods to increase transparency in automated clinical gait classification based on time series. For this purpose, predictions of state-of-the-art...
Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Models
Contemporary learning models for computer vision are typically trained on very large (benchmark) datasets with millions of samples. These may, however, contain biases, artifacts, or errors that have gone unnoticed and are exploitable by the...
Terahertz Multilayer Thickness Measurements: Comparison of Optoelectronic Time and Frequency Domain Systems
We compare a state-of-the-art terahertz (THz) time domain spectroscopy (TDS) system and a novel optoelectronic frequency domain spectroscopy (FDS) system with respect to their performance in layer thickness measurements on dielectric samples....
Inverse kinematics for full-body self representation in VR-based cognitive rehabilitation
Being self-represented through an avatar increases embodiment and the feeling of presence in virtual reality. Nevertheless, currently users in VR are typically represented only by their hands, as not enough tracking data is available for full...
Accurate human body reconstruction for volumetric video
In this work, we enhance a professional end-to-end volumetric video production pipeline to achieve high-fidelity human body reconstruction using only passive cameras.We introduce and optimize deep learning based multi-view stereo networks for...
Fiber-based Frequency Modulated LiDAR With MEMS Scanning Capability for Long-range Sensing in Automotive Applications
Safe operation of driver assistance systems remains a challenge, especially at higher speeds. It requires sensor technology that is capable of detecting surrounding conditions even at large distances. LiDAR technology is a cornerstone of this...
Linearity Characteristics of Avalanche Photodiodes For InP Based PICs
We demonstrate InP based PICs with MMIs and waveguide integrated avalanche photodiodes (APD). We investigate these devices regarding their DC and RF linearity characteristics and find a high bandwidth beyond 20 GHz and a dynamic range of 30 dB...
On the Link between Subjective Score Prediction and Disagreement of Video Quality Metrics
It is common to observe signi?cant disagreements amongst the quality predictions of these VQMs for the same video sequence. Herein, a measure for quantifying the disagreement between VQMs is proposed. We propose a disagreement measure that...
Demonstration of latency-aware 5G network slicing on optical metro networks
The H2020 METRO-HAUL European project has architected a latency-aware, cost-effective, agile, and programmable optical metro network. This includes the design of semidisaggregated metro nodes with compute and storage capabilities, which interface...
Secure Multi-Party Computation and Statistics Sharing for ML Model Training in Multi-domain Multi-vendor Networks
We propose a secure aggregation algorithm that allows proprietary-owned domains, hosting statistically different datasets, train and operate ML models in a Horizontally Federated Learning fashion. The obtained results show a compelling test...
Vertical Federated Learning for Privacy-Preserving ML Model Development in Partially Disaggregated Networks
We present a novel framework that enables vendors and operators, with partial access to operational and monitoring features of a service, to collaboratively develop a ML-assisted solution without revealing any business-critical raw data to each...
Radiation pattern of planar optoelectronic antennas for broadband continuous-wave terahertz emission
In future wireless communication networks at terahertz frequencies, the directivity and the beam profile of the emitters are highly relevant since no additional beam forming optics can be placed in free-space between the emitter and receiver. We...
Can You Do Real-Time Gesture Recognition with 5 Watts?
Accurate and reliable gesture recognition is a central problem in human-computer interaction (HCI). Many applications that make use of gesture recognition call for mobile devices with reduced power consumption, weight and form factors. Recent...
Production environment of tomorrow (ProMo): Partially automated repair process of small tool moulds, forming tools, injection moulding tools and sand casting tools
Small defects in the grain or major damage to a moulded part or tool can bring production to a standstill. SMEs in particular have neither the personnel nor the equipment to repair such damage on their own, so they send it to specialised...
Endoscopic measurement of nasal septum perforations
Nasal septum perforations (NSP) have many uncomfortable symptoms for the patient and a highly negative impact on quality of life. NSPs are closed using patient-specific implants or surgery. Implants are created either under anesthesia using...
Enabling S-C-L-Band Systems with Standard C-Band Modulator and Coherent Receiver using Coherent System Identification and Nonlinear Predistortion
A promising solution to keep up with the rapid growth in global traffic while at the same time addressing increasing network cost, is the efficient reuse of installed legacy optical fiber. Multiband systems are promising solutions to capitalize...
Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors
In this paper, we present Feature Focus, a new transparent face morphing detector based on a modified VGG-A architecture and an additional feature shaping loss function, as well as Focused Layer-wise Relevance Propagation (FLRP), an extension of...
Formation of Titanium Nitride, Titanium Carbide and Silicon Carbide Surfaces by High Power Femtosecond Laser Treatment
Surface treatment with femtosecond laser pulses at high repetition rates in the presence of gaseous sources for nitrogen and carbon leads to the formation of stable coatings with nitrides and carbides. High power femtosecond laser setups fill the...
COMPASS: localization in laparoscopic visceral surgery
Tracking of surgical instruments is an essential step towards the modernization of the surgical workflow by a comprehensive surgical landscape guidance system (COMPASS). Real-time tracking of a laparoscopic camera used in minimally-invasive...
2D Optical Phased Arrays for Laser Beam Steering Based on 3D Polymer Photonic Integrated Circuits
A novel concept for the implementation of 2-dimensional (2D) optical phased arrays (OPAs) with end-fire waveguides as antenna elements (AEs) is proposed and its theoretical model and experimental proof is presented. The concept is based on the...
Influence of losses on the Laser Voltage drop of the active section
A model of a tunable distributed Bragg reflector (DBR) laser describing the effect of cavity losses on the gain voltage is presented. Theoretical and experimental results are in good agreement. Measurements show the gain voltage trace for Bragg...
Influence of losses on the Laser Voltage drop of the active section
A model of a tunable distributed Bragg reflector (DBR) laser describing the effect of cavity losses on the gain voltage is presented. Theoretical and experimental results are in good agreement. Measurements show the gain voltage trace for Bragg...
Interconnection challenges on integrated terahertz photonic systems
Current challenges for RF interconnects are presented, esp. for calibrated measures of the frequency response of components operating > 100 GHz. Photonics and electronics are combined to develop new paradigm in the millimetre and Terahertz...