scholarly journals TET-GAN: Text Effects Transfer via Stylization and Destylization

2019 ◽  
Vol 33 ◽  
pp. 1238-1245 ◽  
Author(s):  
Shuai Yang ◽  
Jiaying Liu ◽  
Wenjing Wang ◽  
Zongming Guo
Keyword(s):  
Network Design ◽  
State Of The Art ◽  
The State ◽  
High Quality ◽  
Style Transfer ◽  
Feature Representations ◽  
Art Methods ◽  
Matching Criteria

Text effects transfer technology automatically makes the text dramatically more impressive. However, previous style transfer methods either study the model for general style, which cannot handle the highly-structured text effects along the glyph, or require manual design of subtle matching criteria for text effects. In this paper, we focus on the use of the powerful representation abilities of deep neural features for text effects transfer. For this purpose, we propose a novel Texture Effects Transfer GAN (TET-GAN), which consists of a stylization subnetwork and a destylization subnetwork. The key idea is to train our network to accomplish both the objective of style transfer and style removal, so that it can learn to disentangle and recombine the content and style features of text effects images. To support the training of our network, we propose a new text effects dataset with as much as 64 professionally designed styles on 837 characters. We show that the disentangled feature representations enable us to transfer or remove all these styles on arbitrary glyphs using one network. Furthermore, the flexible network design empowers TET-GAN to efficiently extend to a new text style via oneshot learning where only one example is required. We demonstrate the superiority of the proposed method in generating high-quality stylized text over the state-of-the-art methods.

Industrial-Scale Production of High-Quality Graphene Sheets by Millstone Grinders

2021 ◽  
Author(s):  
Peng Lv ◽  
Xiaoshi Li ◽  
Zihan Zhang ◽  
Biao Nie ◽  
Yiliang Wu ◽  
...  
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
The State ◽  
Industrial Scale ◽  
Graphene Sheets ◽  
Scale Production ◽  
Large Area ◽  
High Quality ◽  
Art Methods ◽  
Mechanical Cleavage

Abstract Graphene exhibits a variety of unprecedented innate properties and has sparked great interest in both fundamental science and regarding prospective commercial applications. To meet the ever-increasing demand for high-quality graphene sheets, an industrial-scale, reliable, environmental-friendly, low-cost production process is required. However, large-scale production high quality graphene remains elusive. Here we demonstrate a scalable mechanical cleavage method for large-quantity production of high quality large-area and few-layer graphene sheets by introducing a millstone grinding process. The average thickness of the graphene sheets is around 5 nm. This procedure is simpler than the state-of-the-art methods that allows for scalable preparation of graphene dispersion in hundreds of litres by mechanical cleavage of graphite, and the yield is 30-40%. The size of the prepared graphene sheets can be tuneable from few micrometres to tens of micrometres by varying the dimension of raw graphite, which is larger than that produced by the state-of-the-art methods. Moreover, comparing to conductive agents, the conductivity of wafers containing graphene can be increased by one order of magnitude, suggesting a high potential of the prepared graphene sheets for the application as conductive agent in lithium battery cathodes. This allows the requirements of different sizes graphene sheets for industry applications in different fields.

scholarly journals Distribution Aligned Multimodal and Multi-domain Image Stylization

2021 ◽  
Vol 17 (3) ◽  
pp. 1-17
Author(s):  
Minxuan Lin ◽  
Fan Tang ◽  
Weiming Dong ◽  
Xiao Li ◽  
Changsheng Xu ◽  
...  
Keyword(s):  
State Of The Art ◽  
Unified Framework ◽  
High Quality ◽  
Style Transfer ◽  
Multiple Images ◽  
Qualitative And Quantitative ◽  
Image Stylization ◽  
Art Methods ◽  
Artistic Styles ◽  
Painting Style Transfer

Multimodal and multi-domain stylization are two important problems in the field of image style transfer. Currently, there are few methods that can perform multimodal and multi-domain stylization simultaneously. In this study, we propose a unified framework for multimodal and multi-domain style transfer with the support of both exemplar-based reference and randomly sampled guidance. The key component of our method is a novel style distribution alignment module that eliminates the explicit distribution gaps between various style domains and reduces the risk of mode collapse. The multimodal diversity is ensured by either guidance from multiple images or random style codes, while the multi-domain controllability is directly achieved by using a domain label. We validate our proposed framework on painting style transfer with various artistic styles and genres. Qualitative and quantitative comparisons with state-of-the-art methods demonstrate that our method can generate high-quality results of multi-domain styles and multimodal instances from reference style guidance or a random sampled style.

scholarly journals Smoothing vs. sharpening of colour images: Together or separated

2017 ◽  
Vol 2 (1) ◽  
pp. 299-316 ◽  
Author(s):  
Cristina Pérez-Benito ◽  
Samuel Morillas ◽  
Cristina Jordán ◽  
J. Alberto Conejero
Keyword(s):  
Image Denoising ◽  
Gaussian Distribution ◽  
State Of The Art ◽  
Visual Quality ◽  
The State ◽  
Art Methods ◽  
Efficiency And Effectiveness

AbstractIt is still a challenge to improve the efficiency and effectiveness of image denoising and enhancement methods. There exists denoising and enhancement methods that are able to improve visual quality of images. This is usually obtained by removing noise while sharpening details and improving edges contrast. Smoothing refers to the case of denoising when noise follows a Gaussian distribution.Both operations, smoothing noise and sharpening, have an opposite nature. Therefore, there are few approaches that simultaneously respond to both goals. We will review these methods and we will also provide a detailed study of the state-of-the-art methods that attack both problems in colour images, separately.

scholarly journals Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features

2017 ◽  
Vol 108 (1) ◽  
pp. 307-318 ◽  
Author(s):  
Eleftherios Avramidis
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Machine Translation ◽  
State Of The Art ◽  
Linear Method ◽  
The State ◽  
Quality Estimation ◽  
Art Methods ◽  
Improved Performance

AbstractA deeper analysis on Comparative Quality Estimation is presented by extending the state-of-the-art methods with adequacy and grammatical features from other Quality Estimation tasks. The previously used linear method, unable to cope with the augmented features, is replaced with a boosting classifier assisted by feature selection. The methods indicated show improved performance for 6 language pairs, when applied on the output from MT systems developed over 7 years. The improved models compete better with reference-aware metrics.Notable conclusions are reached through the examination of the contribution of the features in the models, whereas it is possible to identify common MT errors that are captured by the features. Many grammatical/fluency features have a good contribution, few adequacy features have some contribution, whereas source complexity features are of no use. The importance of many fluency and adequacy features is language-specific.

Towards Zero Defect Manufacturing paradigm: A review of the state-of-the-art methods and open challenges

2022 ◽  
Vol 134 ◽  
pp. 103548
Author(s):  
Bianca Caiazzo ◽  
Mario Di Nardo ◽  
Teresa Murino ◽  
Alberto Petrillo ◽  
Gianluca Piccirillo ◽  
...  
Keyword(s):  
State Of The Art ◽  
The State ◽  
Art Methods

High-Quality Knowledge Graphs Generation: R2RML and RML Comparison, Rules Validation and Inconsistency Resolution

2020 ◽  
Author(s):  
Anastasia Dimou
Keyword(s):  
State Of The Art ◽  
The State ◽  
Knowledge Graph ◽  
High Quality ◽  
Inconsistency Resolution ◽  
Knowledge Graphs ◽  
Rdf Graphs ◽  
Graph Generation

In this chapter, an overview of the state of the art on knowledge graph generation is provided, with focus on the two prevalent mapping languages: the W3C recommended R2RML and its generalisation RML. We look into details on their differences and explain how knowledge graphs, in the form of RDF graphs, can be generated with each one of the two mapping languages. Then we assess if the vocabulary terms were properly applied to the data and no violations occurred on their use, either using R2RML or RML to generate the desired knowledge graph.

Technical Details and Educational Applications for Virtual Reality Technologies

2021 ◽  
pp. 74-95
Author(s):  
Yongzhi Wang
Keyword(s):  
Higher Education ◽  
Virtual Reality ◽  
Learning Process ◽  
State Of The Art ◽  
The State ◽  
High Quality ◽  
Comprehensive Survey ◽  
Technical Details ◽  
Educational Applications ◽  
Teaching Learning

The application of virtual reality (VR) in higher education has drawn attention. Understanding the state of the art for VR technologies helps educators identify appropriate applications and develop a high-quality engaging teaching-learning process. This chapter provides a comprehensive survey of current hardware and software supports on VR. Secondly, important technical metrics in VR technology are considered with comparisons of different VR devices using identified metrics. Third, there is a focus on software tools and an explore of various development frameworks, which facilitate the implementation of VR applications. With this information as a foundation, there is a VR use in higher education. Finally, there is a discussion of VR applications that can be potentially used in education.

scholarly journals Uniformity Attentive Learning-Based Siamese Network for Person Re-Identification

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3603
Author(s):  
Dasol Jeong ◽  
Hasil Park ◽  
Joongchol Shin ◽  
Donggoo Kang ◽  
Joonki Paik
Keyword(s):  
Large Scale ◽  
Body Shape ◽  
State Of The Art ◽  
The State ◽  
Whole Body ◽  
Distinctive Features ◽  
Common Features ◽  
Siamese Network ◽  
Art Methods ◽  
Triplet Loss

Person re-identification (Re-ID) has a problem that makes learning difficult such as misalignment and occlusion. To solve these problems, it is important to focus on robust features in intra-class variation. Existing attention-based Re-ID methods focus only on common features without considering distinctive features. In this paper, we present a novel attentive learning-based Siamese network for person Re-ID. Unlike existing methods, we designed an attention module and attention loss using the properties of the Siamese network to concentrate attention on common and distinctive features. The attention module consists of channel attention to select important channels and encoder-decoder attention to observe the whole body shape. We modified the triplet loss into an attention loss, called uniformity loss. The uniformity loss generates a unique attention map, which focuses on both common and discriminative features. Extensive experiments show that the proposed network compares favorably to the state-of-the-art methods on three large-scale benchmarks including Market-1501, CUHK03 and DukeMTMC-ReID datasets.

scholarly journals MLVCNN: Multi-Loop-View Convolutional Neural Network for 3D Shape Retrieval

2019 ◽  
Vol 33 ◽  
pp. 8513-8520 ◽  
Author(s):  
Jianwen Jiang ◽  
Di Bao ◽  
Ziqiang Chen ◽  
Xibin Zhao ◽  
Yue Gao
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Shape Representation ◽  
The State ◽  
Shape Retrieval ◽  
3D Shape Retrieval ◽  
3D Shape ◽  
Loop Level ◽  
Art Methods

3D shape retrieval has attracted much attention and become a hot topic in computer vision field recently.With the development of deep learning, 3D shape retrieval has also made great progress and many view-based methods have been introduced in recent years. However, how to represent 3D shapes better is still a challenging problem. At the same time, the intrinsic hierarchical associations among views still have not been well utilized. In order to tackle these problems, in this paper, we propose a multi-loop-view convolutional neural network (MLVCNN) framework for 3D shape retrieval. In this method, multiple groups of views are extracted from different loop directions first. Given these multiple loop views, the proposed MLVCNN framework introduces a hierarchical view-loop-shape architecture, i.e., the view level, the loop level, and the shape level, to conduct 3D shape representation from different scales. In the view-level, a convolutional neural network is first trained to extract view features. Then, the proposed Loop Normalization and LSTM are utilized for each loop of view to generate the loop-level features, which considering the intrinsic associations of the different views in the same loop. Finally, all the loop-level descriptors are combined into a shape-level descriptor for 3D shape representation, which is used for 3D shape retrieval. Our proposed method has been evaluated on the public 3D shape benchmark, i.e., ModelNet40. Experiments and comparisons with the state-of-the-art methods show that the proposed MLVCNN method can achieve significant performance improvement on 3D shape retrieval tasks. Our MLVCNN outperforms the state-of-the-art methods by the mAP of 4.84% in 3D shape retrieval task. We have also evaluated the performance of the proposed method on the 3D shape classification task where MLVCNN also achieves superior performance compared with recent methods.

Sign in / Sign up

Export Citation Format

Share Document