Mohammad Gowayyed
Papers
2
Total Citations
713
H-Index
2
About
Mohammad Gowayyed is a computer vision researcher whose work has made significant contributions to the field of human action recognition, particularly through the analysis of 3D skeletal data and motion trajectories. His research focuses on developing robust descriptors and feature representations that enable machines to accurately interpret and classify human movements from video sequences — a challenge with wide-ranging applications in human-robot interaction, surveillance, multimedia retrieval, and interactive entertainment. Gowayyed's most influential contribution, "Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations" (2013), has accumulated over 530 citations, establishing it as a landmark paper in skeleton-based action recognition. By leveraging covariance descriptors across a temporal hierarchy of 3D joint positions, his approach offered a powerful and elegant solution to capturing complex motion patterns. His complementary work introducing the Histogram of Oriented Displacements (HOD) — a novel descriptor for human joint trajectories — has garnered an additional 181 citations, further demonstrating his ability to devise innovative feature engineering strategies. Together, these contributions reflect a researcher deeply committed to advancing machine understanding of human motion, with a body of work that continues to influence modern action recognition systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2