A. Tanju Erdem
Papers
1
Total Citations
4
H-Index
1
About
Dr. A. Tanju Erdem is a researcher whose work lies at the intersection of computer vision, machine learning, and human motion analysis. His key research areas include unsupervised video analysis, gesture recognition, and 3D motion characterization. Dr. Erdem’s major contribution is a pioneering framework for automatically analyzing dance performances from video without human supervision. By employing Hidden Markov Models (HMMs), his system can identify and segment unknown, repeated dance figures from raw footage, enabling the realistic animation of avatars. This work, detailed in his 2008 paper “Unsupervised dance figure analysis from video for dancing Avatar animation,” has garnered 4 citations and represents a foundational step in bridging the gap between raw visual data and expressive, data-driven animation. Dr. Erdem’s approach is notable for its unsupervised nature, which reduces the need for labor-intensive manual annotation, making it a valuable tool for both computer graphics and human-computer interaction. His research continues to inspire new methods in automated motion understanding and virtual character control.
Research Focus
Key Achievements
Top Papers
- 1