Cees Snoek

Cees Snoek is a researcher at the University of Amsterdam specializing in AI foundation models, multimodal learning, and video analysis. His work focuses on advancing self-supervised learning, generalized category discovery, and multimodal interaction.

Research Highlights:

• Developing revolutionary self-coding models for test-time category discovery
• Creating methods for generalized multimodal learning with unseen modality combinations
• Pioneering Bayesian approaches to improve prompt learning in vision-language models
• Innovating end-to-end graph refinement for object detection
• Advancing motion-focused video representations through tubelet-contrastive learning

His recent work at NeurIPS 2023 and ICCV 2023 demonstrates leadership in solving fundamental challenges in category delineation, multimodal generalization, and 3D point cloud processing. All publications emphasize practical implementation with theoretical foundations.

Scientific Awards:

• Recipient of the Netherlands Prize for ICT research (2012), recognizing innovative contributions to semantic video search technology