Search Results - "Xie, Zecheng"
-
1
DropSample: A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognition
Published in Pattern recognition (01-10-2016)“…Inspired by the theory of Leitner׳s learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural…”
Get full text
Journal Article -
2
Fully convolutional recurrent network for handwritten Chinese text recognition
Published in 2016 23rd International Conference on Pattern Recognition (ICPR) (01-12-2016)“…This paper proposes an end-to-end framework, namely fully convolutional recurrent network (FCRN) for handwritten Chinese text recognition (HCTR). Unlike…”
Get full text
Conference Proceeding -
3
High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps
Published in 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (01-08-2015)“…Just like its great success in solving many computer vision problems, the convolutional neural networks (CNN) provided new end-to-end approach to handwritten…”
Get full text
Conference Proceeding -
4
SCUT-EPT: New Dataset and Benchmark for Offline Chinese Text Recognition in Examination Paper
Published in IEEE access (2019)“…Most existing studies and public datasets for handwritten Chinese text recognition are based on the regular documents with clean and blank background, lacking…”
Get full text
Journal Article -
5
Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge
Published in 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (01-08-2015)“…Deep convolutional neural networks (DCNNs) have achieved great success in various computer vision and pattern recognition applications, including those for…”
Get full text
Conference Proceeding -
6
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
Published in IEEE transactions on pattern analysis and machine intelligence (01-08-2018)“…Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and…”
Get full text
Journal Article -
7
Radical aggregation network for few-shot offline handwritten Chinese character recognition
Published in Pattern recognition letters (01-07-2019)“…•A radical aggregation network for radical-level Chinese character recognition.•We employ deep prototype learning to generate effective and robust radical…”
Get full text
Journal Article -
8
Irregular text block recognition via decoupling visual, linguistic, and positional information
Published in Pattern recognition (01-09-2024)“…Scene text recognition has made great progress in regular formats, and the recent research has focused on irregular text recognition. In this work, we…”
Get full text
Journal Article -
9
Convolutional Multi-directional Recurrent Network for Offline Handwritten Text Recognition
Published in 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) (01-10-2016)“…In this paper, we propose a new network architecture called Convolutional Multi-directional Recurrent Network (CDRN) for offline handwritten text recognition…”
Get full text
Conference Proceeding -
10
PS-LSTM: Capturing Essential Sequential Online Information with Path Signature and LSTM for Writer Identification
Published in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) (01-11-2017)“…Writer identification plays a significant role in several applications including forensic trace evidence identification, mobile bank transaction…”
Get full text
Conference Proceeding -
11
Weakly supervised precise segmentation for historical document images
Published in Neurocomputing (Amsterdam) (20-07-2019)“…With the passing of history, precious cultural heritage was left behind to tell ancient stories, especially those in the form of written documents. In this…”
Get full text
Journal Article -
12
Aggregation Cross-Entropy for Sequence Recognition
Published in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2019)“…In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function…”
Get full text
Conference Proceeding -
13
A Comprehensive Analysis of Misclassified Handwritten Chinese Character Samples by Incorporating Human Recognition
Published in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) (01-11-2017)“…The development of convolutional neural networks (CNN) has led to revolutionary progress in the resolution of the offline handwritten Chinese character…”
Get full text
Conference Proceeding -
14
Tightness-Aware Evaluation Protocol for Scene Text Detection
Published in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2019)“…Evaluation protocols play key role in the developmental progress of text detection methods. There are strict requirements to ensure that the evaluation methods…”
Get full text
Conference Proceeding -
15
Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2023)“…Table structure recognition aims to extract the logical and physical structure of unstructured table images into a machine-readable format. The latest…”
Get full text
Conference Proceeding -
16
M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2023)“…Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion. Most public datasets currently…”
Get full text
Conference Proceeding -
17
A study of clear channel assessment performance for low power wide area networks
Published in 10th International Conference on Wireless Communications, Networking and Mobile Computing (WiCOM 2014) (2014)“…Low power wide area (LPWA) networks are power-constrained and work on industrial, scientific, medical (ISM) bands. The scheme of clear channel assessment (CCA)…”
Get full text
Conference Proceeding -
18
DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming
Published 27-06-2024“…Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense…”
Get full text
Journal Article -
19
Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
Published 13-03-2023“…Table structure recognition aims to extract the logical and physical structure of unstructured table images into a machine-readable format. The latest…”
Get full text
Journal Article -
20
M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
Published 15-05-2023“…Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion. Most public datasets currently…”
Get full text
Journal Article