paper-with-me

홈 › Papers

Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies

2026-04-08 · Carlos Garrido-Munoz, Aniello Panariello, Silvia Cascianelli, Angelo Porrello, Simone Calderara, Jorge Calvo-Zaragoza, Rita Cucchiara arxiv

Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully zero-shot synthetic-to-real generalization setting, where no real data from the target language is available. Our approach learns how model parameters change when moving from synthetic to real handwriting in one or more source languages and transfers this learned correction to new target languages. When using multiple sources, we rely on linguistic similarity to weigh their contrubition when combining them. Experiments across five languages and six architectures show consistent improvements over synthetic-only baselines and reveal that the transferred corrections benefit even languages unrelated to the sources.

📄 PDF Abstract BibTeX arXiv:2604.09713

Code (0)

등록된 구현이 없습니다.

Tasks

Handwritten Text Recognition

Similar Papers 제목 키워드 기반

Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition

2023-05-25 · Dongnan Gui, Kai Chen, Haisong Ding, Qiang Huo

There are more than 80,000 character categories in Chinese while most of them are rarely used. To build a high performance handwritten Chinese character recognition (HCCR) system supporting the full character set with a …

Denoising

Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition

2021-05-31 · Ravi Bhatt, Anuj Rai, Narayanan C. Krishnan, Sukalpa Chanda

Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers). In a real-life scenario, obtaining sample images for al…

Zero-Shot Learning

Zero-Shot Styled Text Image Generation, but Make It Autoregressive

2025-03-21 · CVPR 2025 1 · Vittorio Pippi, Fabio Quattrini, Silvia Cascianelli, Alessio Tonioni 외

Styled Handwritten Text Generation (HTG) has recently received attention from the computer vision and document analysis communities, which have developed several solutions, either GAN- or diffusion-based, that achieved p…

Image GenerationText Generation

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding

2025-01-16 · Kohei Torimi, Ryosuke Yamada, Daichi Otsuka, Kensho Hara 외

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compare…

3D ClassificationZero-shot 3D classificationZero-Shot Learning

GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images

2020-03-05 · ECCV 2020 8 · Lei Kang, Pau Riba, Yaxing Wang, Marçal Rusiñol 외

Although current image generation methods have reached impressive quality levels, they are still unable to produce plausible yet diverse images of handwritten words. On the contrary, when writing by hand, a great variabi…

Handwritten Word GenerationImage Generation