• Publications
  • Influence
Deep Learning for Medical Image Analysis
TLDR
This report describes my research activities in the Hasso Plattner Institute and summarizes my Ph.D. plan and several novels, end-to-end trainable approaches for analyzing medical images using deep learning algorithm. Expand
  • 737
  • 23
  • PDF
Image Captioning with Deep Bidirectional LSTMs
TLDR
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Expand
  • 141
  • 12
  • PDF
Punctuation Prediction for Unsegmented Transcript Based on Word Vector
TLDR
In this paper we propose an approach to predict punctuation marks for unsegmented speech transcript. Expand
  • 49
  • 11
  • PDF
Content Based Lecture Video Retrieval Using Speech and Video Text Information
TLDR
In the last decade e-lecturing has become more and more popular. Expand
  • 133
  • 10
  • PDF
Language Identification Using Deep Convolutional Recurrent Neural Networks
TLDR
We propose a language identification system that solves the problem in the image domain, rather than the audio domain, while maintaining its classification accuracy. Expand
  • 29
  • 5
  • PDF
MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
TLDR
Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. Expand
  • 14
  • 5
  • PDF
Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning
TLDR
We propose an end-to-end trainable deep bidirectional LSTM (Bi-LSTM) model to address the problem. Expand
  • 45
  • 4
  • PDF
A Conditional Adversarial Network for Semantic Segmentation of Brain Tumor
TLDR
We propose an automatic end-to-end trainable architecture for heterogeneous brain tumor segmentation through adversarial training for the BraTS-2017 challenge. Expand
  • 46
  • 3
  • PDF
Lecture Video Indexing and Analysis Using Video OCR Technology
TLDR
We present an approach for automated lecture video indexing based on video OCR technology: Firstly, we developed a video segmenter for an automated slide video structure analysis. Expand
  • 33
  • 3
  • PDF
BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet
Binary Neural Networks (BNNs) can drastically reduce memory size and accesses by applying bit-wise operations instead of standard arithmetic operations. Therefore it could significantly improve theExpand
  • 32
  • 3
  • PDF