Scholar
Zijia Lu
Google Scholar ID: xEGL7NsAAAAJ
PhD in Computer Science, Northeastern University
Citations & Impact
Citations
181
H-index
7
i10-index
7
Publications
12
Co-authors
8
list available
Resume (English only)
Academic Achievements
- Multiple papers accepted to CVPR, including 'DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos' (CVPR 2025), 'FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Fully-Supervised Action Segmentation' (CVPR 2024), and 'Self-Supervised Multi-Object Tracking with Path Consistency' (CVPR 2024).
Research Experience
- Internships at Amazon AWS AI Lab and Microsoft Research during Ph.D. studies; previously worked as a Student Researcher at Chinese Academic of Sciences and an Architecture Summer Intern at NVIDIA.
Education
- Ph.D. in Computer Science, Northeastern University; Dual B.S. in Computer Science and Economics, NYU Shanghai (2019), awarded with NYU University Honors Scholar and Undergraduate Scholarship of University of Chinese Academy of Sciences.
Background
- Research Interests: Video Understanding Methods, particularly data-efficient video-text matching, enhanced computational efficiency, accurate long temporal modeling, and procedural video understanding. Current research focuses on open-world video understanding and video data generation.
Miscellany
- Actively seeking full-time research positions.
