paper-with-me

홈 › Papers

Contrastive Masked Autoencoders for Character-Level Open-Set Writer Identification

2025-01-21 · Xiaowei Jiang, Wenhao Ma, Yiqun Duan, Thomas Do, Chin-Teng Lin

In the realm of digital forensics and document authentication, writer identification plays a crucial role in determining the authors of documents based on handwriting styles. The primary challenge in writer-id is the "open-set scenario", where the goal is accurately recognizing writers unseen during the model training. To overcome this challenge, representation learning is the key. This method can capture unique handwriting features, enabling it to recognize styles not previously encountered during training. Building on this concept, this paper introduces the Contrastive Masked Auto-Encoders (CMAE) for Character-level Open-Set Writer Identification. We merge Masked Auto-Encoders (MAE) with Contrastive Learning (CL) to simultaneously and respectively capture sequential information and distinguish diverse handwriting styles. Demonstrating its effectiveness, our model achieves state-of-the-art (SOTA) results on the CASIA online handwriting dataset, reaching an impressive precision rate of 89.7%. Our study advances universal writer-id with a sophisticated representation learning approach, contributing substantially to the ever-evolving landscape of digital handwriting analysis, and catering to the demands of an increasingly interconnected world.

📄 PDF Abstract BibTeX arXiv:2501.11895

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos

2025-07-16 · Yuchi Ishikawa, Shota Nakada, Hokuto Munakata, Kazuhiro Saito 외

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-…

Image CaptioningRepresentation LearningRetrieval

Fus-MAE: A cross-attention-based data fusion approach for Masked Autoencoders in remote sensing

2024-01-05 · Hugo Chan-To-Hing, Bharadwaj Veeravalli

Self-supervised frameworks for representation learning have recently stirred up interest among the remote sensing community, given their potential to mitigate the high labeling costs associated with curating large satell…

Contrastive LearningRepresentation LearningSelf-Supervised Learning

Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

2023-03-09 · Peng Gao, Renrui Zhang, Rongyao Fang, Ziyi Lin 외

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level…

Contrastive LearningDecoder

Masked autoencoders are effective solution to transformer data-hungry

2022-12-12 · Jiawei Mao, Honggu Zhou, Xuesong Yin, Yuanqi Chang. Binling Nie. Rui Xu

Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a…

Contrastive LearningInductive Bias

CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition

2023-01-15 · Cheng-Ze Lu, Xiaojie Jin, Zhicheng Huang, Qibin Hou 외

Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This work shows that CMAE also trivially gene…

Action RecognitionTemporal Action Localization