Xiameng QIN

Biography

2024.03~now Changan Automobile （长安汽车）

2017.02~2024.03 Baidu VIS (视觉技术部，原深度学习研究院)

2015.07~2017.2  Hanvon Technology Co.,Ltd (汉王科技). 

I have received the PhD degree at School of Computer Science, Beijing Institute of Technology (BIT), under the supervision of Professor Yunde Jia and Jianbing Shen. 

Research Interests

• VLLM / Autonomous driving / Video Generation （2024 ~ Currently）

• Light-weight Transformer (2022 ~ 2024)

• Document Dewarp: Document dewarp, Document enhancement (2019 ~ 2024)

• Document Understanding: VQA, Structure information extraction, multi-modality pre-training (2018 - 2024) [多模态语义结构化,图像+文本+结构信息提取]

• OCR : Image to Text, Image Recognition, Text Detection, Text Recognition (Jul. 2015 - 2024)

Education Experience

• Sep. 2009 - Jun. 2015    PhD, School of Computer Science, BIT

• Sep. 2005 - Jul. 2009   Bachelor, School of Information Engineering, Zhengzhou University

Publications

【2024 ~】

• Mingliang Zhai, Cheng Li, Zengyuan Guo, Ningrui Yang, Xiameng Qin, Sanyuan Zhao, Junyu Han, Yuwei Wu, Ji Tao, Yunde Jia. World knowledge-enhanced Reasoning using Instruction-guided Interactor in Autonomous Driving. AAAI 2025. [PDF]

• Hannan Lu, Xiaohe Wu, Shudong Wang, Xiameng Qin, Xinyu Zhang, Junyu han, Wangmeng Zuo, Ji Tao.  Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention. Arixv 2024.12. [PDF] [Page]

【2019 ~ 2023】

• Beiya Dai, Xing li, Qunyi Xie, Yulin Li, Xiameng Qin, Chengquan Zhang, Kun Yao, Junyu Han. MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary . Arixv 2023. [PDF]

• Yukun Zhai, Xiaoqiang Zhang, Xiameng Qin, Sanyuan Zhao, Xingping Dong, Jianbing Shen. TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision. MIR 2023. [PDF]

• Mingliang Zhai, Yulin Li, Xiameng Qin, Chen Yi, Qunyi Xie, Chengquan Zhang, Kun Yao, Yuwei Wu, Yunde Jia. Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding. IJCAI 2023. [PDF]

• Yuechen Yu, Yulin Li, Chengquan Zhang, Xiaoqiang Zhang, Zengyuan Guo, Xiameng Qin, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang. StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training. ICLR 2023. [PDF][Code]

• Jianjian Cao, Xiameng Qin, Sanyuan Zhao, Jianbing Shen. Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering. TNNLS 2022. [PDF][Code]

• Yulin Li, Yuxi Qian, Yuechen Yu, Xiameng Qin, Chengquan Zhang, Yan Liu, Kun Yao, Yunyu Han, Jingtuo Liu, Errui Ding. StrucTexT: Structured Text Understanding with Multi-Modal Transformers. ACM MM 2021. [PDF][Code]

• He guo, Xiameng Qin, Jiaming Liu, Junyu Han, Jingtuo Liu, Errui Ding. EATEN: Entity-aware Attention for Single Shot Visual Text Extraction.  ICDAR, 2019. [PDF ]

【2010 ~ 2015】

• Xiameng Qin, Jianbing Shen, Xiaoyang Mao, Xuelong Li, Yunde Jia. Structured-Patch Optimization for Dense Correspondence.  IEEE Transactions on Multimedia (TMM) . 17(3):295-306. 2015. [PDF]

• Xiameng Qin, Jianbing Shen, Xiaoyang Mao, Xuelong Li, Yunde Jia. "Robust Match Fusion using Optimization." IEEE Transactions on Cybernetics. In press. 2014. [PDF] [Code]

• Xiameng Qin, Jianbing Shen, Xuelong Li, Yunde Jia. "A new sparse feature-based patch for dense correspondence ." IEEE International Conference on Multimedia & Expo (ICME), 2014.7, Chengdu. [PDF]

• Yanmei Dong, Mingtao Pei, Xiameng Qin. "Vehicle Color Recognition Based on License Plate Color." International Conference on Computational Intelligence and Security (CIS), Accepted, 2014. [PDF]

• Xiameng Qin, Jiaolong Yang, Wei Liang, Mingtao Pei, Yunde Jia. "Stereo Camera Calibration with an Embedded Calibration Device and Scene Features." IEEE International Conference on Robotics and Biomimetics (Robio). pp. 2306-2310, 2012. [PDF]

• Yunde Jia, Xiameng Qin. "An Embedded Calibration Stereovision System." IEEE Intelligent Vehicles Symposium (IV). pp. 1072-1077, 2012. [PDF]

• Yong Duan, Lei Chen, Yucheng Wang, Min Yang, Xiameng Qin, Shaoyang He, Yunde Jia. "A real-time system for 3D recovery of dynamic scene with multiple RGBD imagers." IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). pp. 1-8, 2010. [PDF]

• Yunde Jia, Xiameng Qin, Yucheng Wang. "An Embedded Calibration Stereovision System." National Invention Patent. (NO. 201110325945.5)  [PDF]

My Friends

    Yuwei Wu  ; Jiaolong Yang ;  Yucheng Wang ; Min Yang ;