no code implementations • EMNLP (sdp) 2020 • Thomas van Dongen, Gideon Maillette de Buy Wenniger, Lambert Schomaker
We also show the merit of using more training data and longer input for number of citations prediction.
no code implementations • 19 Nov 2023 • Asmaa Haja, Eric Brouwer, Lambert Schomaker
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.
no code implementations • 15 Aug 2023 • Gideon Maillette de Buy Wenniger, Thomas van Dongen, Lambert Schomaker
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.
1 code implementation • 11 Jul 2023 • Tobias van der Werff, Maruf A. Dhali, Lambert Schomaker
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.
no code implementations • 11 Jun 2023 • Sha Luo, Lambert Schomaker
High-quality and representative data is essential for both Imitation Learning (IL)- and Reinforcement Learning (RL)-based motion planning tasks.
no code implementations • 17 May 2023 • Zhenxing Zhang, Lambert Schomaker
The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal.
1 code implementation • 15 Dec 2022 • Lisa Koopmans, Maruf A. Dhali, Lambert Schomaker
Identifying the production dates of historical manuscripts is one of the main goals for paleographers when studying ancient documents.
no code implementations • 27 Apr 2022 • Zhenxing Zhang, Lambert Schomaker
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.
no code implementations • 2 Mar 2022 • Thomas Reynolds, Maruf A. Dhali, Lambert Schomaker
Researchers continually perform corroborative tests to classify ancient historical documents based on the physical materials of their writing surfaces.
no code implementations • 25 Feb 2022 • Zhenxing Zhang, Lambert Schomaker
3) How to improve the explainability of a text-to-image generation framework?
no code implementations • 17 Nov 2021 • Zhenxing Zhang, Lambert Schomaker
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.
no code implementations • 10 Sep 2021 • Pieter Floris Jacobs, Gideon Maillette de Buy Wenniger, Marco Wiering, Lambert Schomaker
Furthermore, we explore the influence of the query-pool size on the performance of AL.
1 code implementation • 11 Apr 2021 • Sheng He, Lambert Schomaker
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.
no code implementations • 25 Mar 2021 • Sha Luo, Hamidreza Kasaei, Lambert Schomaker
Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration.
no code implementations • 21 Dec 2020 • Thomas van Dongen, Gideon Maillette de Buy Wenniger, Lambert Schomaker
We also show the merit of using more training data and longer input for number of citations prediction.
no code implementations • 5 Nov 2020 • Zhenxing Zhang, Lambert Schomaker
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.
1 code implementation • 27 Oct 2020 • Mladen Popović, Maruf A. Dhali, Lambert Schomaker
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.
no code implementations • EMNLP (sdp) 2020 • Gideon Maillette de Buy Wenniger, Thomas van Dongen, Eleri Aedmaa, Herbert Teun Kruitbosch, Edwin A. Valentijn, Lambert Schomaker
To tackle these problems, we propose the use of HANs combined with structure-tags which mark the role of sentences in the document.
1 code implementation • 16 Mar 2020 • Sheng He, Lambert Schomaker
Writer identification based on a small amount of text is a challenging problem.
no code implementations • 29 Feb 2020 • Tim Oosterhuis, Lambert Schomaker
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.
1 code implementation • 10 Feb 2020 • Yikun Li, Lambert Schomaker, S. Hamidreza Kasaei
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
no code implementations • 7 Feb 2020 • Sha Luo, Hamidreza Kasaei, Lambert Schomaker
Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics.
no code implementations • 11 Dec 2019 • Lambert Schomaker
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.
no code implementations • 6 Dec 2019 • Mahya Ameryan, Lambert Schomaker
In this paper, an end-to-end convolutional LSTM Neural Network is used to handle both geometric variation and sequence variability.
no code implementations • 13 Nov 2019 • Maruf A. Dhali, Jan Willem de Wit, Lambert Schomaker
Handwritten document-image binarization is a semantic segmentation process to differentiate ink pixels from background pixels.
no code implementations • 17 Apr 2019 • Lambert Schomaker
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.
1 code implementation • 28 Feb 2019 • Gideon Maillette de Buy Wenniger, Lambert Schomaker, Andy Way
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
no code implementations • 18 Jan 2019 • Sheng He, Lambert Schomaker
This paper presents a novel iterative deep learning framework and apply it for document enhancement and binarization.
no code implementations • 16th International Conference on Frontiers in Handwriting Recognition (ICFHR 2018) 2018 • Sukalpa Chanda, Jochem Baas, Daniël Haitink, Sebastien Hamely, Dominique Stutzmanny, Lambert Schomaker
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.
no code implementations • 28 Sep 2018 • Sheng He, Lambert Schomaker
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.
no code implementations • 27 Aug 2018 • Sheng He, Lambert Schomaker
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).
no code implementations • 18 Aug 2016 • Lambert Schomaker
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.