Weidong (Tom) Cai
Scholar

Weidong (Tom) Cai

Google Scholar ID: N8qTc2AAAAAJ
School of Computer Science, The University of Sydney
Computer VisionMedical Image ComputingImage/Video ProcessingMachine LearningMultimedia
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
10,571
 
H-index
50
 
i10-index
154
 
Publications
20
 
Co-authors
0
 
Contact
GitHubOpen ↗
Resume
Academic Achievements
  • - Published more than 300 peer-reviewed papers in leading international journals and proceedings of top international conferences
  • - Senior Area Editor of IEEE Transactions on Image Processing, Associate Editor of Computational Visual Media, and Associate Editor of Brain Informatics
  • - Selected Publications:
  • - "ChoreoMuse: Robust Music-to-Dance Video Generation with Style Transfer and Beat-Adherent Motion"
  • - "Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs"
  • - "RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm"
  • - "ScSAM: Debiasing Morphology and Distributional Variability in Subcellular Semantic Segmentation"
  • - "CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detection"
  • - "VRM: Knowledge Distillation via Virtual Relation Matching"
  • - "Medical Image Registration Meets Vision Foundation Model: Prototype Learning and Contour Awareness"
  • - "CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination"
  • - "Multimodal Causal Reasoning Benchmark: Challenging Multimodal Large Language Models to Discern Causal Links"
Research Experience
  • - Lead Investigator / Visiting Professor on medical image analysis and medical computer vision at Harvard Medical School in 2014
Education
  • - PhD: 2001, Basser Department of Computer Science, The University of Sydney
Background
  • - Research Interests: Computer vision, medical image computing, machine learning, image/video processing, multimedia computing, pattern recognition, computer graphics, bioimage informatics, and computational neuroscience
  • - Position: Associate Professor in the School of Computer Science, Director of the Multimedia Laboratory, and Associate Director of the Biomedical & Multimedia Information Technology (BMIT) Research Group at the University of Sydney