Alert button
Picture for Xiameng Qin

Xiameng Qin

Alert button

Collaborative Position Reasoning Network for Referring Image Segmentation

Jan 22, 2024
Jianjian Cao, Beiya Dai, Yulin Li, Xiameng Qin, Jingdong Wang

Viaarxiv icon

MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary

Jul 24, 2023
Beiya Dai, Xing li, Qunyi Xie, Yulin Li, Xiameng Qin, Chengquan Zhang, Kun Yao, Junyu Han

Figure 1 for MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary
Figure 2 for MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary
Figure 3 for MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary
Figure 4 for MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary
Viaarxiv icon

TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision

Jun 06, 2023
Yukun Zhai, Xiaoqiang Zhang, Xiameng Qin, Sanyuan Zhao, Xingping Dong, Jianbing Shen

Figure 1 for TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
Figure 2 for TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
Figure 3 for TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
Figure 4 for TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
Viaarxiv icon

Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding

May 19, 2023
Mingliang Zhai, Yulin Li, Xiameng Qin, Chen Yi, Qunyi Xie, Chengquan Zhang, Kun Yao, Yuwei Wu, Yunde Jia

Figure 1 for Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
Figure 2 for Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
Figure 3 for Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
Figure 4 for Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
Viaarxiv icon

StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training

Mar 01, 2023
Yuechen Yu, Yulin Li, Chengquan Zhang, Xiaoqiang Zhang, Zengyuan Guo, Xiameng Qin, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

Figure 1 for StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Figure 2 for StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Figure 3 for StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Figure 4 for StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Viaarxiv icon

Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering

Dec 14, 2021
JianJian Cao, Xiameng Qin, Sanyuan Zhao, Jianbing Shen

Figure 1 for Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
Figure 2 for Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
Figure 3 for Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
Figure 4 for Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
Viaarxiv icon

StrucTexT: Structured Text Understanding with Multi-Modal Transformers

Aug 10, 2021
Yulin Li, Yuxi Qian, Yuchen Yu, Xiameng Qin, Chengquan Zhang, Yan Liu, Kun Yao, Junyu Han, Jingtuo Liu, Errui Ding

Figure 1 for StrucTexT: Structured Text Understanding with Multi-Modal Transformers
Figure 2 for StrucTexT: Structured Text Understanding with Multi-Modal Transformers
Figure 3 for StrucTexT: Structured Text Understanding with Multi-Modal Transformers
Figure 4 for StrucTexT: Structured Text Understanding with Multi-Modal Transformers
Viaarxiv icon

EATEN: Entity-aware Attention for Single Shot Visual Text Extraction

Sep 20, 2019
He guo, Xiameng Qin, Jiaming Liu, Junyu Han, Jingtuo Liu, Errui Ding

Figure 1 for EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
Figure 2 for EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
Figure 3 for EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
Figure 4 for EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
Viaarxiv icon