Turning a clip model into a scene text detector

W Yu, Y Liu, W Hua, D Jiang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown
great potential in various downstream tasks via leveraging the pretrained vision and …

Omniparser: A unified framework for text spotting key information extraction and table recognition

J Wan, S Song, W Yu, Y Liu, W Cheng… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Recently visually-situated text parsing (VsTP) has experienced notable advancements
driven by the increasing demand for automated document understanding and the …

Odm: A text-image further alignment pre-training approach for scene text detection and spotting

C Duan, P Fu, S Guo, Q Jiang… - Proceedings of the IEEE …, 2024‏ - openaccess.thecvf.com
In recent years text-image joint pre-training techniques have shown promising results in
various tasks. However in Optical Character Recognition (OCR) tasks aligning text instances …

Maskocr: Text recognition with masked encoder-decoder pretraining

P Lyu, C Zhang, S Liu, M Qiao, Y Xu, L Wu… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Text images contain both visual and linguistic information. However, existing pre-training
techniques for text recognition mainly focus on either visual representation learning or …

Towards robust real-time scene text detection: From semantic to instance representation learning

X Qin, P Lyu, C Zhang, Y Zhou, K Yao… - Proceedings of the 31st …, 2023‏ - dl.acm.org
Due to the flexible representation of arbitrary-shaped scene text and simple pipeline, bottom-
up segmentation-based methods begin to be mainstream in real-time scene text detection …

Modeling entities as semantic points for visual information extraction in the wild

Z Yang, R Long, P Wang, S Song… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Abstract Recently, Visual Information Extraction (VIE) has been becoming increasingly
important in both academia and industry, due to the wide range of real-world applications …

Less is more: Removing text-regions improves clip training efficiency and robustness

L Cao, B Zhang, C Chen, Y Yang, X Du… - arxiv preprint arxiv …, 2023‏ - arxiv.org
The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming
the de facto backbone in many applications. However, training a CLIP model from hundreds …

Document parsing unveiled: Techniques, challenges, and prospects for structured information extraction

Q Zhang, VSJ Huang, B Wang, J Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Document parsing is essential for converting unstructured and semi-structured documents-
such as contracts, academic papers, and invoices-into structured, machine-readable data …

Turning a clip model into a scene text spotter

W Yu, Y Liu, X Zhu, H Cao, X Sun… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP)
model to enhance scene text detection and spotting tasks, transforming it into a robust …

Zero-shot object counting with good exemplars

H Zhu, J Yuan, Z Yang, Y Guo, Z Wang… - … on Computer Vision, 2024‏ - Springer
Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names
of object classes during testing, without the need for manual annotations. However, a critical …