Yu Xie

Yu Xie

Auto-generated profile, based on publicly available information

Yu Xie

Bilibili Inc. China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
QQQian Qiao
Qian Qiao
YXYu Xie
Yu Xie
JGJun Gao
Jun Gao
TWTianxiang Wu
Tianxiang Wu
SHShaoyao Huang
Shaoyao Huang
YZYue Zhang
Yue Zhang
More and more end-to-end text spotting methods based on Transformer architecture have demonstrated superior performance. These methods utilize a bipartite graph matching algorithm to perform one-to-one optimal matching between predicted objects and actual objects. However, the instability of bipartite graph matching can lead to inconsistent optimization targets, thereby affecting the training performance of the model. Existing literature applies denoising training to solve the problem of bipartite graph matching instability in object detection tasks. Unfortunately, this denoising training method cannot be directly applied to text spotting tasks, as these tasks need to perform irregular shape detection tasks and more complex text recognition tasks than classification. To address this issue, we propose a novel denoising training method (DNTextSpotter) for arbitrary-shaped text spotting. Specifically, we decompose the queries of the denoising part into noised positional and noised content queries. We use the four Bezier control points of the Bezier center curve to generate the noised positional queries. For the noised content queries, considering that the output of the text in a fixed positional order is not conducive to aligning position with content, we employ a masked character sliding method to initialize noised content queries, thereby assisting in the alignment of text content and position. Additionally, to improve the model's perception of the background, we further utilize an additional loss function for background characters classification in the denoising training part. DNTextSpotter outperforms state-of-the-art methods on four benchmarks-Total-Text, SCUT-CTW1500, ICDAR15, and Inverse-Text-most notably achieving an 11.3% improvement over the best approach on Inverse-Text.

27 March 2026 in Computer Graphics Forum
Verified
Journal Article
Closed access
YXYu Xie
Yu Xie
JZJielei Zhang
Jielei Zhang
PCPengyu Chen
Pengyu Chen
WWWeihang Wang
Weihang Wang
LGLongwen Gao
Longwen Gao
ZLZhouhui Lian
Zhouhui Lian