TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918142234591232 |
|---|---|
| author | Kumar, Rohan Jinka, Jyothi Swaroopa Sarvadevabhatla, Ravi Kiran |
| author_facet | Kumar, Rohan Jinka, Jyothi Swaroopa Sarvadevabhatla, Ravi Kiran |
| contents | Recognizing textual attributes such as bold, italic, underline and strikeout is essential for understanding text semantics, structure, and visual presentation. These attributes highlight key information, making them crucial for document analysis. Existing methods struggle with computational efficiency or adaptability in noisy, multilingual settings. To address this, we introduce TexTAR, a multi-task, context-aware Transformer for Textual Attribute Recognition (TAR). Our novel data selection pipeline enhances context awareness, and our architecture employs a 2D RoPE (Rotary Positional Embedding)-style mechanism to incorporate input context for more accurate attribute predictions. We also introduce MMTAD, a diverse, multilingual, multi-domain dataset annotated with text attributes across real-world documents such as legal records, notices, and textbooks. Extensive evaluations show TexTAR outperforms existing methods, demonstrating that contextual awareness contributes to state-of-the-art TAR performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13151 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images Kumar, Rohan Jinka, Jyothi Swaroopa Sarvadevabhatla, Ravi Kiran Computer Vision and Pattern Recognition Recognizing textual attributes such as bold, italic, underline and strikeout is essential for understanding text semantics, structure, and visual presentation. These attributes highlight key information, making them crucial for document analysis. Existing methods struggle with computational efficiency or adaptability in noisy, multilingual settings. To address this, we introduce TexTAR, a multi-task, context-aware Transformer for Textual Attribute Recognition (TAR). Our novel data selection pipeline enhances context awareness, and our architecture employs a 2D RoPE (Rotary Positional Embedding)-style mechanism to incorporate input context for more accurate attribute predictions. We also introduce MMTAD, a diverse, multilingual, multi-domain dataset annotated with text attributes across real-world documents such as legal records, notices, and textbooks. Extensive evaluations show TexTAR outperforms existing methods, demonstrating that contextual awareness contributes to state-of-the-art TAR performance. |
| title | TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13151 |