Chengquan Zhang

Chengquan Zhang

Auto-generated profile, based on publicly available information

Chengquan Zhang

Baidu Inc

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
29 May 2019
Verified
Book Chapter
Closed access
PDF file
YSYipeng Sun
Yipeng Sun
CZChengquan Zhang
Chengquan Zhang
ZHZuming Huang
Zuming Huang
JLJiaming Liu
Jiaming Liu
JHJunyu Han
Junyu Han
EDErrui Ding
Errui Ding

26 October 2023
Verified
Conference Paper
Open access
XQXugong Qin
Xugong Qin
PLPengyuan Lyu
Pengyuan Lyu
CZChengquan Zhang
Chengquan Zhang
YZYu Zhou
Yu Zhou
KYKun Yao
Kun Yao
WWWeiping Wang
Weiping Wang
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. Despite great progress, these methods show deficiencies in robustness and still suffer from false positives and instance adhesion. Different from existing methods which integrate multiple-granularity features or multiple outputs, we resort to the perspective of representation learning in which auxiliary tasks are utilized to enable the encoder to jointly learn robust features with the main task of per-pixel classification during optimization. For semantic representation learning, we propose global-dense semantic contrast (GDSC), in which a vector is extracted for global semantic representation, then used to perform element-wise contrast with the dense grid features. To learn instance-aware representation, we propose to combine top-down modeling (TDM) with the bottom-up framework to provide implicit instance-level clues for the encoder. With the proposed GDSC and TDM, the encoder network learns stronger representation without introducing any parameters and computations during inference. Equipped with a very light decoder, the detector can achieve more robust real-time scene text detection. Experimental results on four public datasets show that the proposed method can outperform or be comparable to the state-of-the-art on both accuracy and speed. Specifically, the proposed method achieves 87.2% F-measure with 48.2 FPS on Total-Text and 89.6% F-measure with 36.9 FPS on MSRA-TD500 on a single GeForce RTX 2080 Ti GPU.

26 October 2023
Verified
Conference Paper
Open access
PLPengyuan Lyu
Pengyuan Lyu
WMWeihong Ma
Weihong Ma
HWHongyi Wang
Hongyi Wang
YYYuechen Yu
Yuechen Yu
CZChengquan Zhang
Chengquan Zhang
JWJingdong Wang
Jingdong Wang
All tables can be represented as grids. Based on this observation, we propose GridFormer, a novel approach for interpreting unconstrained table structures by predicting the vertex and edge of a grid. First, we propose a flexible table representation in the form of an M X N grid. In this representation, the vertexes and edges of the grid store the localization and adjacency information of the table. Then, we introduce a DETR-style table structure recognizer to efficiently predict this multi-objective information of the grid in a single shot. Specifically, given a set of learned row and column queries, the recognizer directly outputs the vertexes and edges information of the corresponding rows and columns. Extensive experiments on five challenging benchmarks which include wired, wireless, multi-merge-cell, oriented, and distorted tables demonstrate the competitive performance of our model over other methods.

19 August 2023
Verified
Book Chapter
Closed access
PDF file
WYWenwen Yu
Wenwen Yu
CZChengquan Zhang
Chengquan Zhang
HCHaoyu Cao
Haoyu Cao
WHWei Hua
Wei Hua
BLBohan Li
Bohan Li
XBXiang Bai
Xiang Bai

21 April 2024 in Pattern Recognition
Verified
Journal Article
Closed access
ZLZiyan Li
Ziyan Li
LJLianwen Jin
Lianwen Jin
CZChengquan Zhang
Chengquan Zhang
JZJiaxin Zhang
Jiaxin Zhang
ZXZecheng Xie
Zecheng Xie
KYKun Yao
Kun Yao

1 August 2023
Verified
Conference Paper
Open access
PDF file
MZMingliang Zhai
Mingliang Zhai
YLYulin Li
Yulin Li
XQXiameng Qin
Xiameng Qin
CYChen Yi
Chen Yi
QXQunyi Xie
Qunyi Xie
YJYunde Jia
Yunde Jia
Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length. General efficient transformers are challenging to be directly adapted to model document. They are unable to handle the layout representation in documents, e.g. word, line and paragraph, on different granularity levels and seem hard to achieve a good trade-off between efficiency and performance. To tackle the concerns, we propose Fast-StrucTexT, an efficient multi-modal framework based on the StrucTexT algorithm with an hourglass transformer architecture, for visual document understanding. Specifically, we design a modality-guided dynamic token merging block to make the model learn multi-granularity representation and prunes redundant tokens. Additionally, we present a multi-modal interaction module called Symmetry Cross-Attention (SCA) to consider multi-modal fusion and efficiently guide the token mergence. The SCA allows one modality input as query to calculate cross attention with another modality in a dual phase. Extensive experiments on FUNSD, SROIE, and CORD datasets demonstrate that our model achieves the state-of-the-art performance and almost 1.9x faster inference time than the state-of-the-art methods.