Maria Razzhivina

Hi, I'm Maria ๐Ÿ‘พ

AI Researcher, Software Engineer (R&D)

Currently, I work on affective computing and HRI, collaborating with national-level academic institutions and contributing to peer-reviewed publications. I'm also leading the development of next-generation computer vision technologies for healthcare at Mecra.

I hold an M.Comp.Sc. in Computer Vision (hons.) from HSE University and an M.Sc. from the University of Stuttgart (Robotic Construction & Fabrication). My research interests include multimodal learning, humanโ€“robot interaction, and learning-based perception for autonomous systems. Previously, I spent several years working at a robotics company in Shanghai, focusing on computer vision systems for industrial robotic systems and autonomous mobile construction robots.

2D\3D Computer Vision Robotics HRI Affective Computing SLAM

Selected Recent Publications

Weak-to-Strong 3D Object Detection with X-Ray Distillation Weak-to-Strong 3D Object Detection with X-Ray Distillation (dark mode)

Weak-to-Strong 3D Object Detection with X-Ray Distillation

Addresses sparsity and occlusion in LiDAR-based 3D object detection

Do you remember the future? Weak-to-Strong Generalization in 3D Object Detection Do you remember the future? Weak-to-Strong Generalization in 3D Object Detection (dark mode)

Do you remember the future? Weak-to-Strong Generalization in 3D Object Detection

Knowledge distillation for supervised learning

Multi-Track Multimodal Learning on iMiGUE Multi-Track Multimodal Learning on iMiGUE (dark mode)

Multi-Track Multimodal Learning on iMiGUE

Micro-gesture and emotion recognition

Recent News