Search Results for author:
Found 15 papers, 13 papers with code
Weakly Supervised Scene Text Detection using Deep Reinforcement Learning
In this paper we propose a weak supervision method for scene text detection, which makes use of reinforcement learning (RL).
Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data
One of the most pressing problems in the automated analysis of historical documents is the availability of annotated training data.
Handwriting Classification for the Analysis of Art-Historical Documents
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
One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks.
Automatic Matching of Paintings and Descriptions in Art-Historic Archives using Multimodal Analysis
In this project description, we propose an approach to retrieve the associations between images and texts for artworks from art-historic archives.
MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
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.
KISS: Keeping It Simple for Scene Text Recognition
Most of these methods propose novel building blocks for neural networks.
LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks
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.
Learning to Train a Binary Neural Network
In our work, we focus on increasing our understanding of the training process and making it accessible to everyone.
SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task.
SEE: Towards Semi-SupervisedEnd-to-End Scene Text Recognition
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
Language Identification Using Deep Convolutional Recurrent Neural Networks
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
STN-OCR: A single Neural Network for Text Detection and Text Recognition
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
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.
Image Captioning with Deep Bidirectional LSTMs
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning.
