Jinwei     Qi     [Google Profile]   [中文版]

Master Candidate （Supervisor: Prof. Yuxin Peng）

Multimedia Information Processing Lab

Wangxuan Institute of Computer Technology

Peking University

No. 128, Zhong-Guan-Cun North Street

Beijing 100080, China

E-mail: qijinwei@pku.edu.cn

Research Directions

• Cross-media analysis and retrieval
• Cross-media Generation and Reasoning

Education

• Master, Computer Application Technology, Wangxuan Institute of Computer Technology, Peking University, 2016 - 2019
• B.S., Computer Science and Technology, EECS, Peking University, 2012- 2016

Awards

• 2019  Excellent Graduates of Beijing
• 2019  Excellent Graduates of Peking University
• 2019  Excellent Master Thesis Award of ICST, Peking University
• 2018  National scholarship of Peking university
• 2018  Triple-A pacesetter student of Peking university
• 2017  Excellent Student of ICST, Peking University
• 2016  Wang Xuan scholarship of ICST, Peking University
• 2016  Excellent communist of EECS, Peking University
• 2015  Learn progressing title of Peking university
• 2014  Wu-Si scholarship of Peking university
• 2013  Second-class scholarship for Freshmen of Peking university
• 2013  Dongshidongfang scholarship of Peking university
• 2013  The first prize of 10th “Jiang Zehan cup” Mathematical Modeling and Computer Application Competition of Peking university

Publication

1. Jinwei Qi, Yuxin Peng and Yunkan Zhuo, "Life-long Cross-media Correlation Learning", 26th ACM Multimedia Conference (ACM MM), pp. 528-536, Seoul, Korea, Oct. 22-26, 2018.(Oral, Full Paper)(EI)【pdf】
2. Jinwei Qi and Yuxin Peng, "Cross-modal Bidirectional Translation via Reinforcement Learning", 27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 2630-2636, Stockholm, Sweden, Jul. 13-19, 2018.(Oral, Full Paper)(EI)【pdf】
3. Jinwei Qi, Yuxin Peng and Yuxin Yuan, "Cross-media Multi-level Alignment with Relation Attention Network", 27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 892-898, Stockholm, Sweden, Jul. 13-19, 2018.(Oral, Full Paper)(EI)【pdf】
4. Jinwei Qi, Xin Huang and Yuxin Peng, "Cross-media Similarity Metric Learning with Unified Deep Networks", Multimedia Tools and Applications (MTAP), Vol. 76, No. 23, pp. 25109-25127, Dec. 2017.(SCI,EI)【pdf】
5. Yuxin Peng, Jinwei Qi, Zhaoda Ye and Yunkan Zhuo, "Hierarchical Visual-Textual Knowledge Distillation for Life-Long Correlation Learning", International Journal of Computer Vision (IJCV), Vol. 129, No. 4, pp. 921-941, Apr. 2021.(SCI, EI)【pdf】
6. Yuxin Peng, Jinwei Qi and Yunkan Zhuo, "MAVA: Multi-level Adaptive Visual-textual Alignment by Cross-media Bi-attention Mechanism", IEEE Transactions on Image Processing (TIP), Vol. 29, pp. 2728-2741, 2020.(SCI, EI)【pdf】【source code】
7. Yuxin Peng and Jinwei Qi, "Quintuple-media Joint Correlation Learning with Deep Compression and Regularization", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 30, No. 8, pp. 2709-2722, Aug. 2020.(SCI, EI)【pdf】【source code】
8. Yuxin Peng and Jinwei Qi, "Reinforced Cross-Media Correlation Learning by Context-Aware Bidirectional Translation", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 30, No. 6, pp. 1718-1731, Jun. 2020.(SCI, EI)【pdf】【source code】
9. Yuxin Peng and Jinwei Qi, "CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning", ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Vol. 15, No. 1, p. 22, Feb. 2019.(SCI, EI)【pdf】【source code】
10. Yuxin Peng and Jinwei Qi, "Show and Tell in the Loop: Cross-Modal Circular Correlation Learning", IEEE Transactions on Multimedia (TMM), Vol. 21, No. 6, pp. 1538-1550, Jun. 2019.(SCI, EI)【pdf】
11. Yuxin Peng, Jinwei Qi and Yuxin Yuan, "Modality-specific Cross-modal Similarity Measurement with Recurrent Attention Network", IEEE Transactions on Image Processing (TIP), Vol. 27, No. 11, pp. 5585-5599, Nov. 2018.(SCI,EI)【pdf】【source code】
12. Yuxin Peng, Jinwei Qi, Xin Huang and Yuxin Yuan, "CCL: Cross-modal Correlation Learning with Multigrained Fusion by Hierarchical Network", IEEE Transactions on Multimedia (TMM), Vol. 20, No. 2, pp. 405-420, Feb. 2018.(SCI,EI)【pdf】【source code】
13. Yuxin Peng, Zhaoda Ye, Jinwei Qi and Yunkan Zhuo, "Unsupervised Visual-textual Correlation Learning with Fine-grained Semantic Alignment", IEEE Transactions on Cybernetics (TCYB), DOI:10.1109/TCYB.2020.3015084, Sep. 2020. (Accept)【pdf】【source code】
14. Yuxin Peng, Xin Huang and Jinwei Qi, "Cross-media Shared Representation by Hierarchical Learning with Multiple Deep Networks", 25th International Joint Conference on Artificial Intelligence (IJCAI), pp. 3846-3853 , New York City, New York, USA, Jul. 9-15, 2016.(Oral, Full Paper)(EI)【pdf】【source code】
15. 綦金玮, 彭宇新, 袁玉鑫, "面向跨媒体检索的层级循环注意力网络模型", 中国图象图形学报 (Journal of Image and Graphics), Vol. 23, No. 11, pp. 1751-1758, Jul. 2018.【pdf】
16. 彭宇新, 綦金玮, 黄鑫, "多媒体内容理解的研究现状与展望", 计算机研究与发展 (60周年特刊特邀综述论文), 2019年1月, 第56卷第1期, 183~208页.(EI)【pdf】
17. 卓昀侃, 綦金玮, 彭宇新, "跨媒体深层细粒度关联学习方法", 软件学报, 2019年4月, 第30卷第4期, 884~895页.(EI)【pdf】【source code】

Personal Interests

• Badminton