CV

Education

• M.S. in Pattern Recognition and Intelligent Systems, Xidian University, 2020, Advisor: Prof. Jie Feng
• B.S. in Computer Science and Technology, Qingdao University of Science and Technology, 2017

Work experience

• ‌November 2021 - Present: Researcher‌
  • Shanghai Artificial Intelligence Laboratory
  • ‌Duties include‌: Research on embodied intelligence open source and implementation projects.
  • ‌Achievements‌: Complete LLM training, deployment and application. Develop projects with commercial prospects such as rare disease WeChat Q&A robots, intelligent NPC tour guides, and mobile robots with memory mechanisms. Participate in the research of embodied intelligence open source frameworks, including GRUTopia and GRManipulation.
• ‌October 2021 - November 2021: Algorithm Engineer‌
  • SenseTime Technology
  • ‌Duties include‌: Lead the project “Intelligent Nursing System” to complete product design, algorithm development, testing, multiple rounds of POC and PR.
  • ‌Achievements‌: The project has served nearly 100 people with ALS in a non-profit manner, and has gone through 4 rounds of POC, which has been well received by users. The publicity news has covered mainstream media at home and abroad, with a readership of over 10 million.
• ‌July 2020 - October 2021: Algorithm Engineer‌
  • ‌Xiaohongshu‌
  • ‌Duties include‌: Developing a quasi-real-time risk control system based on Flink, Kafka, and Nebula graph database to enhance community traffic risk management.
  • ‌Achievements‌: Implemented community discovery and clustering algorithms, improving real-time interception rates by 60%. Built a community ecological graph based on business needs, enhancing the platform’s ability to identify and combat gray and black industries.

Skills

• Python, C++, PyTorch
• Embodied AI, Vision+X, Data Mining

Publications

Toward Motion Robustness: A masked attention regularization framework in remote photoplethysmography

Zhao, P., Sun, Q., Tian, X., Yang, Y., Tao, S., Cheng, J., & Chen, J. (2024). Toward Motion Robustness: A masked attention regularization framework in remote photoplethysmography. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7829-7838).

Dual-graph convolutional network based on band attention and sparse constraint for hyperspectral band selection

Feng, J., Ye, Z., Liu, S., Zhang, X., Chen, J., Shang, R., & Jiao, L. (2021). Dual-graph convolutional network based on band attention and sparse constraint for hyperspectral band selection. Knowledge-Based Systems, 231, 107428.

Convolutional neural network based on bandwise-independent convolution and hard thresholding for hyperspectral band selection

Feng, J., Chen, J., Sun, Q., Shang, R., Cao, X., Zhang, X., & Jiao, L. (2020). Convolutional neural network based on bandwise-independent convolution and hard thresholding for hyperspectral band selection. IEEE transactions on cybernetics, 51(9), 4414-4428.

Generative adversarial networks based on collaborative learning and attention mechanism for hyperspectral image classification

Feng, J., Feng, X., Chen, J., Cao, X., Zhang, X., Jiao, L., & Yu, T. (2020). Generative adversarial networks based on collaborative learning and attention mechanism for hyperspectral image classification. Remote Sensing, 12(7), 1149.

Hyperspectral band selection based on ternary weight convolutional neural network

Feng, J., Li, D., Chen, J., Zhang, X., Tang, X., & Wu, X. (2019, July). Hyperspectral band selection based on ternary weight convolutional neural network. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (pp. 3804-3807). IEEE.

Joint multilayer spatial-spectral classification of hyperspectral images based on CNN and ConvLSTM

Feng, J., Wu, X., Chen, J., Zhang, X., Tang, X., & Li, D. (2019, July). Joint multilayer spatial-spectral classification of hyperspectral images based on CNN and ConvLSTM. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (pp. 588-591). IEEE.

CNN-based multilayer spatial–spectral feature fusion and sample augmentation with local and nonlocal constraints for hyperspectral image classification

Feng, J., Chen, J., Liu, L., Cao, X., Zhang, X., Jiao, L., & Yu, T. (2019). CNN-based multilayer spatial–spectral feature fusion and sample augmentation with local and nonlocal constraints for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(4), 1299-1313.