Md Mofijul Islam

University of Virginia

Papers

5

Total Citations

135

H-Index

4

About

Md Mofijul Islam is a robotics researcher advancing human-robot interaction through multimodal perception and motion prediction. His work centers on enabling robots to understand and anticipate human behavior in collaborative settings, with key contributions in human activity recognition, team dynamics modeling, and close-proximity collaboration. His most cited paper, "Multi-GAT" (90 citations), introduces a graphical attention-based hierarchical approach for multimodal human activity recognition, addressing the challenge of noisy sensor data in real-world environments. Islam also explores the social dimensions of robotics, as in "Who's Laughing NAO?" (26 citations), which examines how robots can use humor to manage perceptions of failure during interactions. More recently, his work on "PoseTron" (2024) and "IMPRINT" (2023) tackles the critical problem of multi-human motion prediction, enabling safer and more fluent human-robot teamwork in shared spaces. Additionally, his research on pedestrian and cyclist detection using thermal imaging demonstrates a commitment to robust perception for autonomous systems. Through these contributions, Islam is shaping the future of collaborative robotics, where machines can seamlessly anticipate and adapt to human actions.

Research Focus

Key Achievements

4
H-Index
5
Papers
135
Total Citations
27
Avg Citations/Paper
🏆 Most Cited Paper
Multi-GAT: A Graphical Attention-Based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition
90 citations · 2021
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 8
🏛 Institutions: University of Virginia

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 15 days ago