Search Results for author:
Found 32 papers, 7 papers with code
SChuBERT: Scholarly Document Chunks with BERT-encoding boost Citation Count Prediction.
We also show the merit of using more training data and longer input for number of citations prediction.
Self-Supervised Versus Supervised Training for Segmentation of Organoid Images
When trained on only 114 images for the main task, the self-supervised learning approach outperforms the supervised method achieving an F1-score of 0. 85, with higher stability, in contrast to an F1=0. 78 scored by the supervised method.
MultiSChuBERT: Effective Multimodal Fusion for Scholarly Document Quality Prediction
Using BERT$_{\textrm{BASE}}$ embeddings, on the (log) number of citations prediction task with the ACL-BiblioMetry dataset, our MultiSChuBERT (text+visual) model obtains an $R^{2}$ score of 0. 454 compared to 0. 432 for the SChuBERT (text only) model.
Writer adaptation for offline text recognition: An exploration of neural network-based methods
In this paper, we explore how HTR models can be made writer adaptive by using only a handful of examples from a new writer (e. g., 16 examples) for adaptation.
Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning
High-quality and representative data is essential for both Imitation Learning (IL)- and Reinforcement Learning (RL)-based motion planning tasks.
Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation
The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal.
The Effects of Character-Level Data Augmentation on Style-Based Dating of Historical Manuscripts
Identifying the production dates of historical manuscripts is one of the main goals for paleographers when studying ancient documents.
Optimized latent-code selection for explainable conditional text-to-image GANs
In this paper, we present a variety of techniques to take a deep look into the latent space and semantic space of the conditional text-to-image GANs model.
Image-based material analysis of ancient historical documents
Researchers continually perform corroborative tests to classify ancient historical documents based on the physical materials of their writing surfaces.
OptGAN: Optimizing and Interpreting the Latent Space of the Conditional Text-to-Image GANs
3) How to improve the explainability of a text-to-image generation framework?
DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation
In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description.
Active learning for reducing labeling effort in text classification tasks
Furthermore, we explore the influence of the query-pool size on the performance of AL.
GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification
The spatial relationship between the sequence of fragments is modeled by the recurrent neural network (RNN) to strengthen the discriminative ability of the local fragment features.
Self-Imitation Learning by Planning
Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration.
SChuBERT: Scholarly Document Chunks with BERT-encoding boost Citation Count Prediction
We also show the merit of using more training data and longer input for number of citations prediction.
DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation
Most existing text-to-image generation methods adopt a multi-stage modular architecture which has three significant problems: 1) Training multiple networks increases the run time and affects the convergence and stability of the generative model; 2) These approaches ignore the quality of early-stage generator images; 3) Many discriminators need to be trained.
Artificial intelligence based writer identification generates new evidence for the unknown scribes of the Dead Sea Scrolls exemplified by the Great Isaiah Scroll (1QIsaa)
Although many scholars believe that 1QIsaa was written by one scribe, we report new evidence for a breaking point in the series of columns in this scroll.
Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction
To tackle these problems, we propose the use of HANs combined with structure-tags which mark the role of sentences in the document.
FragNet: Writer Identification using Deep Fragment Networks
Writer identification based on a small amount of text is a challenging problem.
"Who is Driving around Me?" Unique Vehicle Instance Classification using Deep Neural Features
Feature maps of a pretrained `YOLO' network are used to create 700 deep integrated feature signatures (DIFS) from 20 different images of 35 vehicles from a high resolution dataset and 340 signatures from 20 different images of 17 vehicles of a lower resolution tracking benchmark dataset.
Learning to Grasp 3D Objects using Deep Residual U-Nets
Affordance detection is one of the challenging tasks in robotics because it must predict the grasp configuration for the object of interest in real-time to enable the robot to interact with the environment.
Robotics
Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning
Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics.
Lifelong learning for text retrieval and recognition in historical handwritten document collections
This chapter provides an overview of the problems that need to be dealt with when constructing a lifelong-learning retrieval, recognition and indexing engine for large historical document collections in multiple scripts and languages, the Monk system.
A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification
In this paper, an end-to-end convolutional LSTM Neural Network is used to handle both geometric variation and sequence variability.
BiNet: Degraded-Manuscript Binarization in Diverse Document Textures and Layouts using Deep Encoder-Decoder Networks
Handwritten document-image binarization is a semantic segmentation process to differentiate ink pixels from background pixels.
A large-scale field test on word-image classification in large historical document collections using a traditional and two deep-learning methods
Additional tests using nearest mean on the output of the pre-final layer of an Inception V3 network, for each book, only yielded mediocre results (mean accuracy 49\%), but was not sensitive to high numbers of classes.
No Padding Please: Efficient Neural Handwriting Recognition
Neural handwriting recognition (NHR) is the recognition of handwritten text with deep learning models, such as multi-dimensional long short-term memory (MDLSTM) recurrent neural networks.
Ranked #15 on
Handwritten Text Recognition
on IAM
DeepOtsu: Document Enhancement and Binarization using Iterative Deep Learning
This paper presents a novel iterative deep learning framework and apply it for document enhancement and binarization.
Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features
A Zero-shot learning algorithm is capable of handling unseen classes, provided the algorithm has been fortified with rich discriminating features and reliable “attribute description” per class during training.
Deep Adaptive Learning for Writer Identification based on Single Handwritten Word Images
Our proposed method transfers the benefits of the learned features of a convolutional neural network from an auxiliary task such as explicit content recognition to the main task of writer identification in a single procedure.
Open Set Chinese Character Recognition using Multi-typed Attributes
Recognition of Off-line Chinese characters is still a challenging problem, especially in historical documents, not only in the number of classes extremely large in comparison to contemporary image retrieval methods, but also new unseen classes can be expected under open learning conditions (even for CNN).
Caveats on Bayesian and hidden-Markov models (v2.8)
This paper describes a number of fundamental and practical problems in the application of hidden-Markov models and Bayes when applied to cursive-script recognition.
