Online Writer Retrieval with Chinese Handwritten Phrases: A Synergistic Temporal-Frequency Representation Learning Approach

TL;DR

This paper introduces DOLPHIN, a novel model for online Chinese handwritten phrase retrieval that combines temporal and frequency features, supported by a large-scale dataset OLIWER, demonstrating superior performance and insights into feature importance.

Contribution

The paper presents DOLPHIN, a new synergistic temporal-frequency learning model, and introduces OLIWER, a large-scale Chinese handwritten phrase dataset for online writer retrieval.

Findings

DOLPHIN outperforms existing methods in retrieval accuracy.

Frequency and pressure features significantly improve handwriting representation.

Cross-domain retrieval benefits from increased feature alignment.

Abstract

Currently, the prevalence of online handwriting has spurred a critical need for effective retrieval systems to accurately search relevant handwriting instances from specific writers, known as online writer retrieval. Despite the growing demand, this field suffers from a scarcity of well-established methodologies and public large-scale datasets. This paper tackles these challenges with a focus on Chinese handwritten phrases. First, we propose DOLPHIN, a novel retrieval model designed to enhance handwriting representations through synergistic temporal-frequency analysis. For frequency feature learning, we propose the HFGA block, which performs gated cross-attention between the vanilla temporal handwriting sequence and its high-frequency sub-bands to amplify salient writing details. For temporal feature learning, we propose the CAIR block, tailored to promote channel interaction and reduce channel redundancy. Second, to address data deficit, we introduce OLIWER, a large-scale online writer retrieval dataset encompassing over 670,000 Chinese handwritten phrases from 1,731 individuals. Through extensive evaluations, we demonstrate the superior performance of DOLPHIN over existing methods. In addition, we explore cross-domain writer retrieval and reveal the pivotal role of increasing feature alignment in bridging the distributional gap between different handwriting data. Our findings emphasize the significance of point sampling frequency and pressure features in improving handwriting representation quality and retrieval performance. Code and dataset are available at https://github.com/SCUT-DLVCLab/DOLPHIN.