Denis Dresvyanskiy

Papers

Total Citations

H-Index

About

Denis Dresvyanskiy is a researcher at the forefront of affective computing and human behavior analysis, with a primary focus on engagement recognition using deep learning. His most cited work, "Deep Learning Based Engagement Recognition in Highly Imbalanced Data" (2021), addresses a critical challenge in the field: accurately detecting user engagement from video data when disengaged states vastly outnumber engaged ones. By developing robust deep learning architectures that handle severe class imbalance, Dresvyanskiy has advanced the reliability of automated engagement estimation—a key component for applications in education, human-robot interaction, and mental health monitoring. With 19 citations, this paper has already influenced subsequent work on imbalanced learning in affective computing. His contributions are notable for bridging the gap between theoretical deep learning methods and practical, real-world deployment, where data distributions are rarely ideal. Dresvyanskiy’s research continues to push the boundaries of how machines interpret human attention and involvement, making him a rising voice in the intersection of computer vision and psychology.