Marco Keller

Karlsruhe Institute of Technology

Papers

1

Total Citations

2

H-Index

1

About

Marco Keller is a rising researcher at the forefront of computer vision and human-robot interaction, with a specialized focus on bridging the gap between synthetic data and real-world action recognition. His work addresses a critical bottleneck in robotics: the need for large, diverse, and privacy-compliant training datasets for household environments. Keller’s most notable contribution, the 2024 paper “SynthAct: Towards Generalizable Human Action Recognition based on Synthetic Data,” introduces a novel framework that leverages procedurally generated synthetic data to train models for recognizing human activities, bypassing the costly and intrusive process of real-world data collection. This work is foundational for enabling safer and more intuitive human-robot collaboration in domestic settings, where privacy concerns often limit data availability. While still early in his career, with SynthAct already garnering 2 citations, Keller’s approach represents a significant step toward scalable, privacy-preserving AI. His research promises to make household robots more adaptable and context-aware, positioning him as a key voice in the future of embodied AI and synthetic data generation.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
SynthAct: Towards Generalizable Human Action Recognition based on Synthetic Data
2 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: Karlsruhe Institute of Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago