activity
20162023
most citedCTC-Segmentation of Large Corpora for German End-to-end Speech Recognition

79 citations · 179 across the 17 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

7 papers · 2 filters

cs.CV2021

The Box Size Confidence Bias Harms Your Object Detector

Johannes Gilg, Torben Teepe, Fabian Herzog +1

Countless applications depend on accurate predictions with reliable confidence estimates from modern object detectors. It is well known, however, that neural networks including obj…

cs.CV2021

Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Martin Knoche, Stefan Hörmann, Gerhard Rigoll

Real-world face recognition applications often deal with suboptimal image quality or resolution due to different capturing conditions such as various subject-to-camera distances, p…

cs.CV2021

Susceptibility to Image Resolution in Face Recognition and Trainings Strategies

Martin Knoche, Stefan Hörmann, Gerhard Rigoll

Face recognition approaches often rely on equal image resolution for verifying faces on two images. However, in practical applications, those image resolutions are usually not in t…

cs.CV2021

Attention-based Partial Face Recognition

Stefan Hörmann, Zeyuan Zhang, Martin Knoche +2

Photos of faces captured in unconstrained environments, such as large crowds, still constitute challenges for current face recognition approaches as often faces are occluded by obj…

cs.CV2021

How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild

Okan Köpüklü, Maja Taseska, Gerhard Rigoll

Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a referenc…

cs.CV2021

Lightweight Multi-Branch Network for Person Re-Identification

Fabian Herzog, Xunbo Ji, Torben Teepe +3

Person Re-Identification aims to retrieve person identities from images captured by multiple cameras or the same cameras in different time instances and locations. Because of its i…