TY  - CONF
AU  - Alloy Das
AU  - Sanket Biswas
AU  - Ayan Banerjee
AU  - Josep Llados
AU  - Umapada Pal
AU  - Saumik Bhattacharya
A2  - WACV
PY  - 2024//
TI  - Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
BT  - Winter Conference on Applications of Computer Vision
SP  - 718
EP  - 728
N2  - The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and recognition simply by pretraining on natural scene text datasets, which do not directly exploit the intermediate feature representations between multiple domains. Here, we investigate the problem of domain-adaptive scene text spotting, i.e., training a model on multi-domain source data such that it can directly adapt to target domains rather than being specialized for a specific domain or scenario. Further, we investigate a transformer baseline called Swin-TESTR to focus on solving scene-text spotting for both regular and arbitrary-shaped scene text along with an exhaustive evaluation. The results clearly demonstrate the potential of intermediate representations to achieve significant performance on text spotting benchmarks across multiple domains (e.g. language, synth-to-real, and documents). both in terms of accuracy and efficiency.
UR  - https://openaccess.thecvf.com/content/WACV2024/html/Das_Harnessing_the_Power_of_Multi-Lingual_Datasets_for_Pre-Training_Towards_Enhancing_WACV_2024_paper.html
L1  - http://refbase.cvc.uab.es/files/DBB2023.pdf
N1  - DAG
ID  - Alloy Das2024
ER  -