Font Shape-to-Impression Translation
- URL: http://arxiv.org/abs/2203.05808v1
- Date: Fri, 11 Mar 2022 09:02:25 GMT
- Title: Font Shape-to-Impression Translation
- Authors: Masaya Ueda, Akisato Kimura, Seiichi Uchida
- Abstract summary: This paper tackles part-based shape-impression analysis based on the Transformer architecture.
It is able to handle the correlation among local parts by its self-attention mechanism.
- Score: 15.228202509283248
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Different fonts have different impressions, such as elegant, scary, and cool.
This paper tackles part-based shape-impression analysis based on the
Transformer architecture, which is able to handle the correlation among local
parts by its self-attention mechanism. This ability will reveal how
combinations of local parts realize a specific impression of a font. The
versatility of Transformer allows us to realize two very different approaches
for the analysis, i.e., multi-label classification and translation. A
quantitative evaluation shows that our Transformer-based approaches estimate
the font impressions from a set of local parts more accurately than other
approaches. A qualitative evaluation then indicates the important local parts
for a specific impression.
Related papers
- Font Impression Estimation in the Wild [7.542892664684078]
We use a font dataset with annotation about font impressions and a convolutional neural network (CNN) framework for this task.
We propose an exemplar-based impression estimation approach, which relies on a strategy of ensembling impressions of exemplar fonts that are similar to the input image.
We conduct a correlation analysis between book genres and font impressions on real book cover images.
arXiv Detail & Related papers (2024-02-23T10:00:25Z) - Local Style Awareness of Font Images [8.91092846430013]
When we compare fonts, we often pay attention to styles of local parts, such as serifs and curvatures.
This paper proposes an attention mechanism to find important local parts.
The local parts with larger attention are then considered important.
arXiv Detail & Related papers (2023-10-10T06:13:09Z) - Few shot font generation via transferring similarity guided global style
and quantization local style [11.817299400850176]
We present a novel font generation approach by aggregating styles from character similarity-guided global features and stylized component-level representations.
Our AFFG method could obtain a complete set of component-level style representations, and also control the global glyph characteristics.
arXiv Detail & Related papers (2023-09-02T05:05:40Z) - Multilingual Extraction and Categorization of Lexical Collocations with
Graph-aware Transformers [86.64972552583941]
We put forward a sequence tagging BERT-based model enhanced with a graph-aware transformer architecture, which we evaluate on the task of collocation recognition in context.
Our results suggest that explicitly encoding syntactic dependencies in the model architecture is helpful, and provide insights on differences in collocation typification in English, Spanish and French.
arXiv Detail & Related papers (2022-05-23T16:47:37Z) - Scalable Font Reconstruction with Dual Latent Manifolds [55.29525824849242]
We propose a deep generative model that performs typography analysis and font reconstruction.
Our approach enables us to massively scale up the number of character types we can effectively model.
We evaluate on the task of font reconstruction over various datasets representing character types of many languages.
arXiv Detail & Related papers (2021-09-10T20:37:43Z) - A Multi-Implicit Neural Representation for Fonts [79.6123184198301]
font-specific discontinuities like edges and corners are difficult to represent using neural networks.
We introduce textitmulti-implicits to represent fonts as a permutation-in set of learned implict functions, without losing features.
arXiv Detail & Related papers (2021-06-12T21:40:11Z) - Rethinking Text Line Recognition Models [57.47147190119394]
We consider two decoder families (Connectionist Temporal Classification and Transformer) and three encoder modules (Bidirectional LSTMs, Self-Attention, and GRCLs)
We compare their accuracy and performance on widely used public datasets of scene and handwritten text.
Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length.
arXiv Detail & Related papers (2021-04-15T21:43:13Z) - AAformer: Auto-Aligned Transformer for Person Re-Identification [82.45385078624301]
We introduce an alignment scheme in transformer architecture for the first time.
We propose the auto-aligned transformer (AAformer) to automatically locate both the human parts and nonhuman ones at patch level.
AAformer integrates the part alignment into the self-attention and the output [PART]s can be directly used as part features for retrieval.
arXiv Detail & Related papers (2021-04-02T08:00:25Z) - Which Parts determine the Impression of the Font? [0.0]
Various fonts give different impressions, such as legible, rough, and comic-text.
By focusing on local shapes instead of the whole letter shape, we can realize letter-shape independent and more general analysis.
arXiv Detail & Related papers (2021-03-26T02:13:24Z) - Multiscale Mesh Deformation Component Analysis with Attention-based
Autoencoders [49.62443496989065]
We propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder.
The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions.
With our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes.
arXiv Detail & Related papers (2020-12-04T08:30:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.