@phdthesis{Yang2019,
  author    = {Yang, Haojin},
  title     = {Deep representation learning for multimedia data analysis},
  school      = {Universit{\"a}t Potsdam},
  pages     = {278},
  year      = {2019},
  language  = {en}
}
@article{RezaeiYangMeinel2020,
  author    = {Rezaei, Mina and Yang, Haojin and Meinel, Christoph},
  title     = {Recurrent generative adversarial network for learning imbalanced medical image semantic segmentation},
  series = {Multimedia tools and applications : an international journal},
  volume    = {79},
  journal   = {Multimedia tools and applications : an international journal},
  number    = {21-22},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1380-7501},
  doi       = {10.1007/s11042-019-7305-1},
  pages     = {15329 -- 15348},
  year      = {2020},
  abstract  = {We propose a new recurrent generative adversarial architecture named RNN-GAN to mitigate imbalance data problem in medical image semantic segmentation where the number of pixels belongs to the desired object are significantly lower than those belonging to the background. A model trained with imbalanced data tends to bias towards healthy data which is not desired in clinical applications and predicted outputs by these networks have high precision and low recall. To mitigate imbalanced training data impact, we train RNN-GAN with proposed complementary segmentation mask, in addition, ordinary segmentation masks. The RNN-GAN consists of two components: a generator and a discriminator. The generator is trained on the sequence of medical images to learn corresponding segmentation label map plus proposed complementary label both at a pixel level, while the discriminator is trained to distinguish a segmentation image coming from the ground truth or from the generator network. Both generator and discriminator substituted with bidirectional LSTM units to enhance temporal consistency and get inter and intra-slice representation of the features. We show evidence that the proposed framework is applicable to different types of medical images of varied sizes. In our experiments on ACDC-2017, HVSMR-2016, and LiTS-2017 benchmarks we find consistently improved results, demonstrating the efficacy of our approach.},
  language  = {en}
}
@misc{BartzYangMeinel2018,
  author    = {Bartz, Christian and Yang, Haojin and Meinel, Christoph},
  title     = {SEE: Towards semi-supervised end-to-end scene text recognition},
  series = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, Thirtieth Innovative Applications of Artificial Intelligence Conference, Eight Symposium on Educational Advances in Artificial Intelligence},
  volume    = {10},
  journal   = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, Thirtieth Innovative Applications of Artificial Intelligence Conference, Eight Symposium on Educational Advances in Artificial Intelligence},
  publisher = {ASSOC Association for the Advancement of Artificial Intelligence},
  address   = {Palo Alto},
  isbn      = {978-1-57735-800-8},
  pages     = {6674 -- 6681},
  year      = {2018},
  abstract  = {Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In recent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Most existing works consist of multiple deep neural networks and several pre-processing steps. In contrast to this, we propose to use a single deep neural network, that learns to detect and recognize text from natural images, in a semi-supervised way. SEE is a network that integrates and jointly learns a spatial transformer network, which can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We introduce the idea behind our novel approach and show its feasibility, by performing a range of experiments on standard benchmark datasets, where we achieve competitive results.},
  language  = {en}
}