Visual semantics allow for textual reasoning better in scene text recognition

Y He, C Chen, J Zhang, J Liu, F He, C Wang… - Proceedings of the AAAI …, 2022 - ojs.aaai.org
… shape scene text. To address this issue, we make the first attempt to perform textual reasoning
based on visual semantics in this paper. Technically, given the character segmentation …

Towards accurate scene text recognition with semantic reasoning networks

D Yu, X Li, C Zhang, T Liu, J Han… - … pattern recognition, 2020 - openaccess.thecvf.com
semantic reasoning network (SRN) for accurate scene text recognition, where a global
semantic reasoning module (GSRM) is introduced to capture global semantic context through …

Visual-semantic transformer for scene text recognition

X Tang, Y Lai, Y Liu, Y Fu, R Fang - arXiv preprint arXiv:2112.00948, 2021 - arxiv.org
semantic and visual information jointly with a Visual-… visual-semantic transformer to solve
scene text recognition problem. The VST consists of three model explicitly extract semantic

Seed: Semantics enhanced encoder-decoder framework for scene text recognition

Z Qiao, Y Zhou, D Yang, Y Zhou… - … pattern recognition, 2020 - openaccess.thecvf.com
… In this work, we propose a semantics enhanced encoder-decoder framework to robustly …
We propose SEED for scene text recognition, which predicts additional global semantic

Beyond visual semantics: Exploring the role of scene text in image understanding

AU Dey, SK Ghosh, E Valveny, G Harit - Pattern Recognition Letters, 2021 - Elsevier
scene text and visual channels for robust semantic interpretation of images. We not only extract
and encode visual and scene text … irrelevant or erroneous scene text recognition, we also …

Hierarchical visual-semantic interaction for scene text recognition

L Diao, X Tang, J Wang, G Xie, J Hu - Information Fusion, 2024 - Elsevier
… In this section, we will present our hierarchical visual-semantic interaction (HVSI) method
for scene text recognition. The overview of HVSI is illustrated in Fig. 2, which consists of three …

Visual semantic reasoning for image-text matching

K Li, Y Zhang, K Li, Y Li, Y Fu - … on computer vision, 2019 - openaccess.thecvf.com
… of image usually lacks global semantic concepts as in its corresponding text caption. To …
to generate visual representation that captures key objects and semantic concepts of a scene. …

Multi-modal text recognition networks: Interactive enhancements between visual and semantic features

B Na, Y Kim, S Park - European Conference on Computer Vision, 2022 - Springer
… great benefits to scene text recognition by providing semantics to refine character sequences.
… not fully utilized the semantics to understand visual clues for text recognition. This paper …

Joint visual semantic reasoning: Multi-stage decoder for text recognition

AK Bhunia, A Sain, A Kumar, S Ghose… - … on computer vision, 2021 - openaccess.thecvf.com
… , we argue that semantic information offers a complementary role in addition to visual only. …
Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint …

Svtr: Scene text recognition with a single visual model

Y Du, Z Chen, C Jia, X Yin, T Zheng, C Li, Y Du… - arXiv preprint arXiv …, 2022 - arxiv.org
… Single Visual model for Scene Text recognition within … Scene text recognition aims to
transcript a text in natural image to digital character sequence, which conveys high-level semantics