Scholar
Yu ZHOU (周宇)
Google Scholar ID: FNfBHg8AAAAJ
Nankai University, China
Citations & Impact
Citations
2,342
H-index
25
i10-index
51
Publications
20
Co-authors
19
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Research Experience
- Leading InTimeLab
- Organizing and participating in academic conferences and workshops, such as CSIG Document Image Analysis and Recognition Committee Forum, National Conference on Intelligent Analysis of Ethnic Ancient Documents
- Delivering invited talks at PRCV 2025, ICDAR 2025, VALSE 2025, CCIG 2025, etc.
- Co-organizing the ICDAR 2025 Workshop on Visual Text Generation and Text Image Processing
- Serving as Area Chair for ACM MM 2025
Background
- Professor and PhD Supervisor at Nankai University
- Head of InTimeLab
- Research interests include computer vision, multimodal AI, embodied intelligence, natural language processing, large models, and deep learning
- Specific topics: visual language processing (text, graphics, formulas, tables, charts, flowcharts, mind maps, maps, CAD drawings, sheet music, etc.), OCR, EEG, lip movements, gestures & sign language, actions & behaviors, emotion & sentiment analysis
- Embodied and GUI-based intelligent agents
- Multimodal large models and content generation
- Deep learning and AI safety
