• Publications
  • Influence
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
  • 144
  • 12
  • 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
  • 30
  • 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
  • 17
  • 5
  • 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
  • 35
  • 3
  • PDF
STN-OCR: A single Neural Network for Text Detection and Text Recognition
TLDR
We present STN-OCR, a step towards semi-supervised neural networks for scene text recognition, that can be optimized end-to-end. Expand
  • 39
  • 2
  • PDF
SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
TLDR
We present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Expand
  • 33
  • 1
  • PDF
Learning to Train a Binary Neural Network
TLDR
We evaluate different network architectures and hyperparameters to provide useful insights on how to train a binary neural network and show how to create efficient models. Expand
  • 8
  • 1
  • PDF
SceneTextReg: A Real-Time Video OCR System
TLDR
We showcase a system for real-time video text recognition by using a standard laptop with webcam. Expand
  • 4
  • PDF
KISS: Keeping It Simple for Scene Text Recognition
TLDR
We introduce a new model for scene text recognition that only consists of off-the-shelf building blocks for neural networks. Expand
  • 5
  • PDF