Samira Sheikhi
École Polytechnique Fédérale de Lausanne, Idiap Research Institute
Papers
6
Total Citations
130
H-Index
5
About
Samira Sheikhi is a leading researcher in human-robot interaction (HRI), with a core focus on enabling robots to understand and respond to human non-verbal cues. Her work centers on visual focus of attention (VFOA) recognition, gaze mapping, and addressee estimation—critical skills for robots engaging in natural, multi-party conversations. Sheikhi’s most influential contribution is the development of a dynamic head pose–gaze mapping system that integrates the robot’s conversational state to improve attention recognition, a paper cited over 65 times. She also pioneered the VERNISSAGE Corpus, a multimodal HRI dataset with extensive annotations for benchmarking tasks like speaker localization and VFOA recognition, providing a foundational resource for the field. Her research on context-aware addressee estimation and the “midline effect” for VFOA recognition has advanced how robots interpret who is speaking to whom in group settings. With over 130 total citations, Sheikhi’s work has significantly shaped the design of socially aware robots, making human-machine interaction more intuitive and effective. Her contributions are essential for students and researchers aiming to build robots that can seamlessly collaborate with people in real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Recognizing the Visual Focus of Attention for Human Robot Interaction27 citations · 2012
- 3THE VERNISSAGE CORPUS: A MULTIMODAL HUMAN-ROBOT-INTERACTION DATASET15 citations · 2012
- 4Context aware addressee estimation for human robot interaction10 citations · 2013
- 5Investigating the midline effect for visual focus of attention recognition10 citations · 2012
- 6