1 code implementation • 13 Jan 2022 • Emanuel Metzenthin, Christian Bartz, Christoph Meinel
In this paper we propose a weak supervision method for scene text detection, which makes use of reinforcement learning (RL).
2 code implementations • 14 Jul 2021 • Christian Bartz, Hendrik Raetz, Jona Otholt, Christoph Meinel, Haojin Yang
One of the most pressing problems in the automated analysis of historical documents is the availability of annotated training data.
1 code implementation • 4 Nov 2020 • Christian Bartz, Hendrik Rätz, Christoph Meinel
In this paper, we focus on the analysis of handwriting in scanned documents from the art-historic archive of the WPI.
General Classification Optical Character Recognition (OCR) +2
1 code implementation • 21 Oct 2020 • Christian Bartz, Joseph Bethge, Haojin Yang, Christoph Meinel
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks.
no code implementations • LREC 2020 • Christian Bartz, Nitisha Jain, Ralf Krestel
In this project description, we propose an approach to retrieve the associations between images and texts for artworks from art-historic archives.
1 code implementation • 16 Jan 2020 • Joseph Bethge, Christian Bartz, Haojin Yang, Ying Chen, Christoph Meinel
However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks.
1 code implementation • 19 Nov 2019 • Christian Bartz, Joseph Bethge, Haojin Yang, Christoph Meinel
Most of these methods propose novel building blocks for neural networks.
1 code implementation • 14 Nov 2018 • Christian Bartz, Haojin Yang, Joseph Bethge, Christoph Meinel
Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student.
1 code implementation • 27 Sep 2018 • Joseph Bethge, Haojin Yang, Christian Bartz, Christoph Meinel
In our work, we focus on increasing our understanding of the training process and making it accessible to everyone.
2 code implementations • 14 Dec 2017 • Christian Bartz, Haojin Yang, Christoph Meinel
Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task.
no code implementations • AAAI 2017 • Christian Bartz, Haojin Yang, Christoph Meinel
Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task.
Ranked #2 on Optical Character Recognition (OCR) on FSNS - Test
1 code implementation • 16 Aug 2017 • Christian Bartz, Tom Herold, Haojin Yang, Christoph Meinel
Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
3 code implementations • 27 Jul 2017 • Christian Bartz, Haojin Yang, Christoph Meinel
In contrast to most existing works that consist of multiple deep neural networks and several pre-processing steps we propose to use a single deep neural network that learns to detect and recognize text from natural images in a semi-supervised way.
Ranked #5 on Scene Text Detection on ICDAR 2013
3 code implementations • 27 May 2017 • Haojin Yang, Martin Fritzsche, Christian Bartz, Christoph Meinel
Binary Neural Networks (BNNs) can drastically reduce memory size and accesses by applying bit-wise operations instead of standard arithmetic operations.
1 code implementation • 4 Apr 2016 • Cheng Wang, Haojin Yang, Christian Bartz, Christoph Meinel
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning.