De Cheng
Scholar

De Cheng

Google Scholar ID: 180lASkAAAAJ
Associate Professor, Xidian University
Computer VisionDeep LearningMachine LearningData Compression
Citations & Impact
All-time
Citations
2,667
 
H-index
26
 
i10-index
44
 
Publications
20
 
Co-authors
7
list available
Contact
No contact links provided.
Resume (English only)
Academic Achievements
  • Published over 100 papers in top-tier venues including CVPR, ICCV, NeurIPS, ICML, IJCAI, IJCV, TIP, T-NNLS, T-Cybernetics, and T-CSVT
  • Over 50 first-author or corresponding-author papers in CCF-A conferences and中科院1区 TOP journals
  • Two ESI Highly Cited Papers
  • Single first-author paper cited over 1,600 times
  • Notable works include CVPR 2016 (1600+ citations), multiple IJCV 2025 papers, and CCF-A conference papers in CVPR/ICCV/ICML 2025
Research Experience
  • Joined Xidian University’s ISN National Key Laboratory in January 2021 through talent recruitment
  • Principal investigator of two NSFC General Programs
  • Leading a sub-project of the National Key R&D Program of China
  • Leading Shaanxi Provincial Key R&D Program
  • Leading key sub-projects of NSFC Regional Joint Fund
  • Also leading open projects from key laboratories, fundamental research grants from central universities, and aerospace institute projects
  • Participates in multiple national and provincial-level research initiatives
Background
  • Associate Professor and Doctoral Supervisor at School of Telecommunications Engineering, Xidian University
  • Huashan Scholar Elite Associate Professor
  • Member of the National Key Laboratory of Integrated Service Networks for Air-Space-Ground (ISN)
  • Former Principal Engineer at Huawei
  • Research interests: Computer Vision, Machine Learning, Artificial Intelligence, including prompt learning for large models, video content analysis and understanding (person re-identification, object detection and tracking, video grounding, image fusion), unsupervised/semi-supervised learning, domain generalization, continual learning, and learning with noisy labels