AbstractOnline learning environments, such as Massive Open Online Courses (MOOCs), often rely on videos as a major component to convey knowledge. However, these videos exclude potential participants who do not understand the lecturer's language, regardless of whether that is due to language unfamiliarity or aural handicaps. Subtitles and/or interactive transcripts solve this issue, ease navigation based on the content, and enable indexing and retrieval by search engines. Although there are several automated speech-to-text converters and translation tools, their quality varies and the process of integrating them can be quite tedious. Thus, in practice, many videos on MOOC platforms only receive subtitles after the course is already finished (if at all) due to a lack of resources. This work describes an approach to tackle this issue by providing a dedicated tool, which is closing this gap between MOOC platforms and transcription and translation tools and offering a simple workflow that can easily be handled by users with a less technical background. The proposed method is designed and evaluated by qualitative interviews with three major MOOC providers.
MeliusNet: An Improved Network Architecture for Binary Neural Networks. Bethge, Joseph; Bartz, Christian; Yang, Haojin; Chen, Ying; Meinel, Christoph (2021).
One model to reconstruct them all: A novel way to use the stochastic noise in StyleGAN. Bartz, Christian; Bethge, Joseph; Yang, Haojin; Meinel, Christoph (2020).
Synthetic Data for the Analysis of Archival Documents: Handwriting Determination. Bartz, Christian; Seidel, Laurenz; Nguyen, Duy-Hung; Bethge, Joseph; Yang, Haojin; Meinel, Christoph (2020). 1–8.
Synthetic Data for the Analysis of Archival Documents: Handwriting Determination. Bartz, Christian; Seidel, Laurenz; Nguyen, Duy-Hung; Bethge, Joseph; Yang, Haojin; Meinel, Christoph (2020).
BMXNet 2: An Open Source Framework for Low-bit Networks-Reproducing, Understanding, Designing and Showcasing. Bethge, Joseph; Bartz, Christian; Yang, Haojin; Meinel, Christoph (2020). 4469–4472.
Kiss: Keeping it simple for scene text recognition. Bartz, Christian; Bethge, Joseph; Yang, Haojin; Meinel, Christoph in arXiv preprint arXiv:1911.08400 (2019).
LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks. Bartz, Christian; Yang, Haojin; Bethge, Joseph; Meinel, Christoph G. Carneiro, S. You (reds.) (2019). 341–356.
AbstractRecently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. 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. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also show the simplicity of creating a new dataset, based on a few videos (e.g. downloaded from YouTube) and artificially generated data.
BinaryDenseNet: Developing an Architecture for Binary Neural Networks. Bethge, Joseph; Yang, Haojin; Bornstein, Marvin; Meinel, Christoph (2019).
AbstractBinary neural networks are a promising approach to execute convolutional neural networks on devices with low computational power. Previous work on this subject often quantizes pretrained full-precision models and uses complex training strategies. In our work, we focus on increasing the performance of binary neural networks by training from scratch with a simple training strategy. In our experiments we show that we are able to achieve state-of-the-art results on standard benchmark datasets. Further, we analyze how full-precision network structures can be adapted for efficient binary networks and adopt a network architecture based on a DenseNet for binary networks, which lets us improve the state-of-the-art even further. Our source code can be found online: https://github.com/hpi-xnor/BMXNet-v2
Loans: Weakly supervised object detection with localizer assessor networks. Bartz, Christian; Yang, Haojin; Bethge, Joseph; Meinel, Christoph (2018). 341–356.
Improving Layout Quality by Mixing Treemap-Layouts Based on Data-Change Characteristics. Bethge, Joseph; Hahn, Sebastian; Döllner, Jürgen M. Hullin, R. Klein, T. Schultz, A. Yao (reds.) (2017). (Vol. 2017)
AbstractThis paper presents a hybrid treemap layout approach that optimizes layout-quality metrics by combining state-of-the-art treemap layout algorithms. It utilizes machine learning to predict those metrics based on data metrics describing the characteristics and changes of the dataset. For this, the proposed approach uses a neural network which is trained on artificially generated dataset,s containing a total of 15.8 million samples. The resulting model is integrated into an approach called Smart-Layouting. This approach is evaluated on real-world data from 100 publicly available software repositories. Compared to other state-of-the-art treemap algorithms it reaches an overall better result. Additionally, this approach can be customized by an end user’s needs. The customization allows for specifying weights for the importance of each layout-quality metric. The results indicate, that the algorithm is able to adapt successfully towards a given set of weights.
Relative Direction Change: A Topology-based Metric for Layout Stability in Treemaps. Hahn, Sebastian; Bethge, Joseph; Döllner, Jürgen (2017).
