Junya Obara
Papers
2
Total Citations
11
H-Index
2
About
Junya Obara is a researcher specializing in multi-modal human activity recognition, with a particular focus on integrating motion, audio, and video data for gesture and action understanding. His work bridges computer vision and sensor-based analysis, advancing how machines interpret complex human behaviors. In his most-cited paper, "Multi-modal gesture recognition using integrated model of motion, audio and video" (2015, 6 citations), Obara proposed a novel framework that fuses heterogeneous sensory inputs to improve recognition accuracy in real-world scenarios. He further explored the potential of somatosensory information alone in "Action recognition from only somatosensory information using spectral learning in a hidden Markov model" (2016, 5 citations), demonstrating that meaningful action patterns can be extracted even without visual or audio cues. These contributions are particularly valuable for applications in human-computer interaction, assistive robotics, and ambient intelligence, where robust and efficient recognition is critical. Obara’s work exemplifies a systematic approach to leveraging complementary data modalities, offering practical solutions for systems that must operate under varying sensory conditions. His research continues to influence the development of more adaptive and context-aware recognition technologies.
Research Focus
Key Achievements
Top Papers
- 1
- 2