Aggregated Text Transformer for Scene Text Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910470943801344 |
|---|---|
| author | Zhou, Zhao Du, Xiangcheng Zheng, Yingbin Jin, Cheng |
| author_facet | Zhou, Zhao Du, Xiangcheng Zheng, Yingbin Jin, Cheng |
| contents | This paper explores the multi-scale aggregation strategy for scene text detection in natural images. We present the Aggregated Text TRansformer(ATTR), which is designed to represent texts in scene images with a multi-scale self-attention mechanism. Starting from the image pyramid with multiple resolutions, the features are first extracted at different scales with shared weight and then fed into an encoder-decoder architecture of Transformer. The multi-scale image representations are robust and contain rich information on text contents of various sizes. The text Transformer aggregates these features to learn the interaction across different scales and improve text representation. The proposed method detects scene texts by representing each text instance as an individual binary mask, which is tolerant of curve texts and regions with dense instances. Extensive experiments on public scene text detection datasets demonstrate the effectiveness of the proposed framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_13984 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Aggregated Text Transformer for Scene Text Detection Zhou, Zhao Du, Xiangcheng Zheng, Yingbin Jin, Cheng Computer Vision and Pattern Recognition This paper explores the multi-scale aggregation strategy for scene text detection in natural images. We present the Aggregated Text TRansformer(ATTR), which is designed to represent texts in scene images with a multi-scale self-attention mechanism. Starting from the image pyramid with multiple resolutions, the features are first extracted at different scales with shared weight and then fed into an encoder-decoder architecture of Transformer. The multi-scale image representations are robust and contain rich information on text contents of various sizes. The text Transformer aggregates these features to learn the interaction across different scales and improve text representation. The proposed method detects scene texts by representing each text instance as an individual binary mask, which is tolerant of curve texts and regions with dense instances. Extensive experiments on public scene text detection datasets demonstrate the effectiveness of the proposed framework. |
| title | Aggregated Text Transformer for Scene Text Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2211.13984 |