|
Records |
Links |
|
Author |
Fernando Vilariño |
|
|
Title |
Public Libraries Exploring how technology transforms the cultural experience of people |
Type |
Conference Article |
|
Year |
2019 |
Publication |
Workshop on Social Impact of AI. Open Living Lab Days Conference. |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Thessaloniki; Grecia; September 2019 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
MV; DAG; 600.140; 600.121;SIAI |
Approved |
no |
|
|
Call Number |
Admin @ si @ Vil2019b |
Serial |
3458 |
|
Permanent link to this record |
|
|
|
|
Author |
Fernando Vilariño |
|
|
Title |
Unveiling the Social Impact of AI |
Type |
Conference Article |
|
Year |
2020 |
Publication |
Workshop at Digital Living Lab Days Conference |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
September 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
MV; DAG; 600.121; 600.140;SIAI |
Approved |
no |
|
|
Call Number |
Admin @ si @ Vil2020 |
Serial |
3459 |
|
Permanent link to this record |
|
|
|
|
Author |
Debora Gil; Oriol Ramos Terrades; Raquel Perez |
|
|
Title |
Topological Radiomics (TOPiomics): Early Detection of Genetic Abnormalities in Cancer Treatment Evolution |
Type |
Conference Article |
|
Year |
2020 |
Publication |
Women in Geometry and Topology |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Barcelona; September 2019 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
IAM; DAG; 600.139; 600.145; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ GRP2020 |
Serial |
3473 |
|
Permanent link to this record |
|
|
|
|
Author |
Sanket Biswas; Pau Riba; Josep Llados; Umapada Pal |
|
|
Title |
DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis |
Type |
Conference Article |
|
Year |
2021 |
Publication |
16th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
|
|
Volume |
12823 |
Issue |
|
Pages |
555–568 |
|
|
Keywords |
|
|
|
Abstract |
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout. In this work, given a spatial layout (bounding boxes with object categories) as a reference by the user, our proposed DocSynth model learns to generate a set of realistic document images consistent with the defined layout. Also, this framework has been adapted to this work as a superior baseline model for creating synthetic document image datasets for augmenting real data during training for document layout analysis tasks. Different sets of learning objectives have been also used to improve the model performance. Quantitatively, we also compare the generated results of our model with real data using standard evaluation metrics. The results highlight that our model can successfully generate realistic and diverse document images with multiple objects. We also present a comprehensive qualitative analysis summary of the different scopes of synthetic image generation tasks. Lastly, to our knowledge this is the first work of its kind. |
|
|
Address |
Lausanne; Suissa; September 2021 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
DAG; 600.121; 600.140; 110.312 |
Approved |
no |
|
|
Call Number |
Admin @ si @ BRL2021a |
Serial |
3573 |
|
Permanent link to this record |
|
|
|
|
Author |
Armin Mehri; Parichehr Behjati Ardakani; Angel Sappa |
|
|
Title |
LiNet: A Lightweight Network for Image Super Resolution |
Type |
Conference Article |
|
Year |
2021 |
Publication |
25th International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
7196-7202 |
|
|
Keywords |
|
|
|
Abstract |
This paper proposes a new lightweight network, LiNet, that enhancing technical efficiency in lightweight super resolution and operating approximately like very large and costly networks in terms of number of network parameters and operations. The proposed architecture allows the network to learn more abstract properties by avoiding low-level information via multiple links. LiNet introduces a Compact Dense Module, which contains set of inner and outer blocks, to efficiently extract meaningful information, to better leverage multi-level representations before upsampling stage, and to allow an efficient information and gradient flow within the network. Experiments on benchmark datasets show that the proposed LiNet achieves favorable performance against lightweight state-of-the-art methods. |
|
|
Address |
Virtual; January 2021 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
MSIAU; 600.130; 600.122 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MAS2021a |
Serial |
3583 |
|
Permanent link to this record |
|
|
|
|
Author |
Shiqi Yang; Yaxing Wang; Joost Van de Weijer; Luis Herranz; Shangling Jui |
|
|
Title |
Generalized Source-free Domain Adaptation |
Type |
Conference Article |
|
Year |
2021 |
Publication |
19th IEEE International Conference on Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
8958-8967 |
|
|
Keywords |
|
|
|
Abstract |
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the target domain. However, those methods do not consider keeping source performance which is of high practical value in real world applications. In this paper, we propose a new domain adaptation paradigm called Generalized Source-free Domain Adaptation (G-SFDA), where the learned model needs to perform well on both the target and source domains, with only access to current unlabeled target data during adaptation. First, we propose local structure clustering (LSC), aiming to cluster the target features with its semantically similar neighbors, which successfully adapts the model to the target domain in the absence of source data. Second, we propose sparse domain attention (SDA), it produces a binary domain specific attention to activate different feature channels for different domains, meanwhile the domain attention will be utilized to regularize the gradient during adaptation to keep source information. In the experiments, for target performance our method is on par with or better than existing DA and SFDA methods, specifically it achieves state-of-the-art performance (85.4%) on VisDA, and our method works well for all domains after adapting to single or multiple target domains. |
|
|
Address |
Virtual; October 2021 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP; 600.120; 600.147 |
Approved |
no |
|
|
Call Number |
Admin @ si @ YWW2021 |
Serial |
3605 |
|
Permanent link to this record |
|
|
|
|
Author |
Meysam Madadi; Hugo Bertiche; Wafa Bouzouita; Isabelle Guyon; Sergio Escalera |
|
|
Title |
Learning Cloth Dynamics: 3D+Texture Garment Reconstruction Benchmark |
Type |
Conference Article |
|
Year |
2021 |
Publication |
Proceedings of Machine Learning Research |
Abbreviated Journal |
|
|
|
Volume |
133 |
Issue |
|
Pages |
57-76 |
|
|
Keywords |
|
|
|
Abstract |
Human avatars are important targets in many computer applications. Accurately tracking, capturing, reconstructing and animating the human body, face and garments in 3D are critical for human-computer interaction, gaming, special effects and virtual reality. In the past, this has required extensive manual animation. Regardless of the advances in human body and face reconstruction, still modeling, learning and analyzing human dynamics need further attention. In this paper we plan to push the research in this direction, e.g. understanding human dynamics in 2D and 3D, with special attention to garments. We provide a large-scale dataset (more than 2M frames) of animated garments with variable topology and type, calledCLOTH3D++. The dataset contains RGBA video sequences paired with its corresponding 3D data. We pay special care to garment dynamics and realistic rendering of RGB data, including lighting, fabric type and texture. With this dataset, we hold a competition at NeurIPS2020. We design three tracks so participants can compete to develop the best method to perform 3D garment reconstruction in a sequence from (1) 3D-to-3D garments, (2) RGB-to-3D garments, and (3) RGB-to-3D garments plus texture. We also provide a baseline method, based on graph convolutional networks, for each track. Baseline results show that there is a lot of room for improvements. However, due to the challenging nature of the problem, no participant could outperform the baselines. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HUPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ MBB2021 |
Serial |
3655 |
|
Permanent link to this record |
|
|
|
|
Author |
Sanket Biswas; Pau Riba; Josep Llados; Umapada Pal |
|
|
Title |
Graph-Based Deep Generative Modelling for Document Layout Generation |
Type |
Conference Article |
|
Year |
2021 |
Publication |
16th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
|
|
Volume |
12917 |
Issue |
|
Pages |
525-537 |
|
|
Keywords |
|
|
|
Abstract |
One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, the principal information of its content is stored in the layout itself. In this work, we have proposed an automated deep generative model using Graph Neural Networks (GNNs) to generate synthetic data with highly variable and plausible document layouts that can be used to train document interpretation systems, in this case, specially in digital mailroom applications. It is also the first graph-based approach for document layout generation task experimented on administrative document images, in this case, invoices. |
|
|
Address |
Lausanne; Suissa; September 2021 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
DAG; 600.121; 600.140; 110.312 |
Approved |
no |
|
|
Call Number |
Admin @ si @ BRL2021 |
Serial |
3676 |
|
Permanent link to this record |
|
|
|
|
Author |
Carles Onielfa; Carles Casacuberta; Sergio Escalera |
|
|
Title |
Influence in Social Networks Through Visual Analysis of Image Memes |
Type |
Conference Article |
|
Year |
2022 |
Publication |
Artificial Intelligence Research and Development |
Abbreviated Journal |
|
|
|
Volume |
356 |
Issue |
|
Pages |
71-80 |
|
|
Keywords |
|
|
|
Abstract |
Memes evolve and mutate through their diffusion in social media. They have the potential to propagate ideas and, by extension, products. Many studies have focused on memes, but none so far, to our knowledge, on the users that post them, their relationships, and the reach of their influence. In this article, we define a meme influence graph together with suitable metrics to visualize and quantify influence between users who post memes, and we also describe a process to implement our definitions using a new approach to meme detection based on text-to-image area ratio and contrast. After applying our method to a set of users of the social media platform Instagram, we conclude that our metrics add information to already existing user characteristics. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HuPBA; no menciona |
Approved |
no |
|
|
Call Number |
Admin @ si @ OCE2022 |
Serial |
3799 |
|
Permanent link to this record |
|
|
|
|
Author |
Mohamed Ramzy Ibrahim; Robert Benavente; Daniel Ponsa; Felipe Lumbreras |
|
|
Title |
SWViT-RRDB: Shifted Window Vision Transformer Integrating Residual in Residual Dense Block for Remote Sensing Super-Resolution |
Type |
Conference Article |
|
Year |
2024 |
Publication |
19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Remote sensing applications, impacted by acquisition season and sensor variety, require high-resolution images. Transformer-based models improve satellite image super-resolution but are less effective than convolutional neural networks (CNNs) at extracting local details, crucial for image clarity. This paper introduces SWViT-RRDB, a new deep learning model for satellite imagery super-resolution. The SWViT-RRDB, combining transformer with convolution and attention blocks, overcomes the limitations of existing models by better representing small objects in satellite images. In this model, a pipeline of residual fusion group (RFG) blocks is used to combine the multi-headed self-attention (MSA) with residual in residual dense block (RRDB). This combines global and local image data for better super-resolution. Additionally, an overlapping cross-attention block (OCAB) is used to enhance fusion and allow interaction between neighboring pixels to maintain long-range pixel dependencies across the image. The SWViT-RRDB model and its larger variants outperform state-of-the-art (SoTA) models on two different satellite datasets in terms of PSNR and SSIM. |
|
|
Address |
Roma; Italia; February 2024 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
MSIAU |
Approved |
no |
|
|
Call Number |
Admin @ si @ RBP2024 |
Serial |
4004 |
|
Permanent link to this record |
|
|
|
|
Author |
Ricardo Toledo; S. Sallent; J. Paradell; Juan J. Villanueva |
|
|
Title |
CARE: Computer Assisted Radiology Environment |
Type |
Conference Article |
|
Year |
1995 |
Publication |
Pattern Recognition and image analysis: preprints of the VI National Symposium on Pattern Recogniotion & Image Analysis |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
|
Approved |
no |
|
|
Call Number |
Admin @ si @ |
Serial |
4025 |
|
Permanent link to this record |
|
|
|
|
Author |
Mohammad Rouhani; E. Boyer; Angel Sappa |
|
|
Title |
Non-Rigid Registration meets Surface Reconstruction |
Type |
Conference Article |
|
Year |
2014 |
Publication |
International Conference on 3D Vision |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
617-624 |
|
|
Keywords |
|
|
|
Abstract |
Non rigid registration is an important task in computer vision with many applications in shape and motion modeling. A fundamental step of the registration is the data association between the source and the target sets. Such association proves difficult in practice, due to the discrete nature of the information and its corruption by various types of noise, e.g. outliers and missing data. In this paper we investigate the benefit of the implicit representations for the non-rigid registration of 3D point clouds. First, the target points are described with small quadratic patches that are blended through partition of unity weighting. Then, the discrete association between the source and the target can be replaced by a continuous distance field induced by the interface. By combining this distance field with a proper deformation term, the registration energy can be expressed in a linear least square form that is easy and fast to solve. This significantly eases the registration by avoiding direct association between points. Moreover, a hierarchical approach can be easily implemented by employing coarse-to-fine representations. Experimental results are provided for point clouds from multi-view data sets. The qualitative and quantitative comparisons show the outperformance and robustness of our framework. %in presence of noise and outliers. |
|
|
Address |
Tokyo; Japan; December 2014 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
3DV |
|
|
Notes |
ADAS; 600.055; 600.076 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RBS2014 |
Serial |
2534 |
|
Permanent link to this record |
|
|
|
|
Author |
Pau Baiget; Joan Soto; Xavier Roca; Jordi Gonzalez |
|
|
Title |
Automatic Generation of Computer-Animated Sequences based on Human Behaviour Modelling |
Type |
Conference Article |
|
Year |
2007 |
Publication |
10th International Conference on Computer Graphics and Artificial Intelligence |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Athens (Greece) |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
3IA |
|
|
Notes |
ISE |
Approved |
no |
|
|
Call Number |
ISE @ ise @ BSR2007 |
Serial |
808 |
|
Permanent link to this record |
|
|
|
|
Author |
Xinhang Song; Luis Herranz; Shuqiang Jiang |
|
|
Title |
Depth CNNs for RGB-D Scene Recognition: Learning from Scratch Better than Transferring from RGB-CNNs |
Type |
Conference Article |
|
Year |
2017 |
Publication |
31st AAAI Conference on Artificial Intelligence |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
RGB-D scene recognition; weakly supervised; fine tune; CNN |
|
|
Abstract |
Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to learn depth features combining local weakly supervised training from patches followed by global fine tuning with images. This strategy is capable of learning very discriminative depth-specific features with limited depth images, without resorting to Places-CNN. In addition we propose a modified CNN architecture to further match the complexity of the model and the amount of data available. For RGB-D scene recognition, depth and RGB features are combined by projecting them in a common space and further leaning a multilayer classifier, which is jointly optimized in an end-to-end network. Our framework achieves state-of-the-art accuracy on NYU2 and SUN RGB-D in both depth only and combined RGB-D data. |
|
|
Address |
San Francisco CA; February 2017 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
AAAI |
|
|
Notes |
LAMP; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ SHJ2017 |
Serial |
2967 |
|
Permanent link to this record |
|
|
|
|
Author |
Mohamed Ali Souibgui; Sanket Biswas; Andres Mafla; Ali Furkan Biten; Alicia Fornes; Yousri Kessentini; Josep Llados; Lluis Gomez; Dimosthenis Karatzas |
|
|
Title |
Text-DIAE: a self-supervised degradation invariant autoencoder for text recognition and document enhancement |
Type |
Conference Article |
|
Year |
2023 |
Publication |
Proceedings of the 37th AAAI Conference on Artificial Intelligence |
Abbreviated Journal |
|
|
|
Volume |
37 |
Issue |
2 |
Pages |
|
|
|
Keywords |
Representation Learning for Vision; CV Applications; CV Language and Vision; ML Unsupervised; Self-Supervised Learning |
|
|
Abstract |
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement. We start by employing a transformer-based architecture that incorporates three pretext tasks as learning objectives to be optimized during pre-training without the usage of labelled data. Each of the pretext objectives is specifically tailored for the final downstream tasks. We conduct several ablation experiments that confirm the design choice of the selected pretext tasks. Importantly, the proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time requiring substantially fewer data samples to converge. Finally, we demonstrate that our method surpasses the state-of-the-art in existing supervised and self-supervised settings in handwritten and scene text recognition and document image enhancement. Our code and trained models will be made publicly available at https://github.com/dali92002/SSL-OCR |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
AAAI |
|
|
Notes |
DAG |
Approved |
no |
|
|
Call Number |
Admin @ si @ SBM2023 |
Serial |
3848 |
|
Permanent link to this record |