Stanislav V. Panev

Robotics Institute

Carnegie Mellon University

210 Smith Hall

5000 Forbes Ave.

Pittsburgh, PA 15213

I am a Project Scientist at the Robotics Institute at Carnegie Mellon University. My research focuses on computer vision, with an emphasis on aerial and satellite imagery analysis, generative and foundation models, synthetic data, and adversarial robustness. My work explores how modern generative models can be leveraged to diagnose, improve, and stress-test visual recognition systems, particularly in challenging real-world and defense-related scenarios.

I have contributed to multiple research projects funded by the U.S. Department of Defense, addressing problems such as cross-domain object detection, adversarial camouflage, and synthetic data generation for machine learning. My publications appear in leading venues, including ICCV, WACV, ICIP, and IEEE Transactions on ITS, and my recent work investigates integrating generative AI into evaluation and active learning pipelines.

In addition to my research, I actively mentor graduate students and serve as a reviewer for major computer vision conferences, including CVPR, ICCV, and WACV, where I was recognized as an Outstanding Reviewer in 2024. I received my Ph.D. in Electrical Engineering and Computer Science from the Technical University of Sofia.

selected publications

ICCV

Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision

Xiao Fang, Minhyek Jeon, Zheyang Qin, Stanislav Panev, Celso De Melo, Shuowen Hu, Shayok Chakraborty, and Fernando De La Torre

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2025

arXiv Bib HTML

@inproceedings{Fang_2025_ICCV,
  author = {Fang, Xiao and Jeon, Minhyek and Qin, Zheyang and Panev, Stanislav and De Melo, Celso and Hu, Shuowen and Chakraborty, Shayok and De La Torre, Fernando},
  title = {Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = oct,
  year = {2025},
  pages = {8088-8099},
}

WACV

Exploring the Impact of Rendering Method and Motion Quality on Model Performance When Using Multi-View Synthetic Data for Action Recognition

Stanislav Panev^*, Emily Kim^*, Sai Abhishek Si Namburu, Desislava Nikolova, Celso De Melo, Fernando De La Torre, and Jessica Hodgins

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024

Bib HTML

@inproceedings{Panev_2024_WACV,
  author = {Panev, Stanislav and Kim, Emily and Namburu, Sai Abhishek Si and Nikolova, Desislava and De Melo, Celso and De La Torre, Fernando and Hodgins, Jessica},
  title = {Exploring the Impact of Rendering Method and Motion Quality on Model Performance When Using Multi-View Synthetic Data for Action Recognition},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  month = jan,
  year = {2024},
  pages = {4592-4602},
}

MDPI Sensors
Parkinson’s Disease Tremor Detection in the Wild Using Wearable Accelerometers

Rubén San-Segundo, Ada Zhang, Alexander Cebulla, Stanislav Panev, Griffin Tabor, Katelyn Stebbins, Robyn E. Massa, Andrew Whitford, Fernando De La Torre, and Jessica Hodgins

Sensors, 2020

Abs DOI Bib HTML

Continuous in-home monitoring of Parkinson’s Disease (PD) symptoms might allow improvements in assessment of disease progression and treatment effects. As a first step towards this goal, we evaluate the feasibility of a wrist-worn wearable accelerometer system to detect PD tremor in the wild (uncontrolled scenarios). We evaluate the performance of several feature sets and classification algorithms for robust PD tremor detection in laboratory and wild settings. We report results for both laboratory data with accurate labels and wild data with weak labels. The best performance was obtained using a combination of a pre-processing module to extract information from the tremor spectrum (based on non-negative factorization) and a deep neural network for learning relevant features and detecting tremor segments. We show how the proposed method is able to predict patient self-report measures, and we propose a new metric for monitoring PD tremor (i.e., percentage of tremor over long periods of time), which may be easier to estimate the start and end time points of each tremor event while still providing clinically useful information.
@article{s20205817, author = {San-Segundo, Rubén and Zhang, Ada and Cebulla, Alexander and Panev, Stanislav and Tabor, Griffin and Stebbins, Katelyn and Massa, Robyn E. and Whitford, Andrew and De La Torre, Fernando and Hodgins, Jessica}, title = {Parkinson’s Disease Tremor Detection in the Wild Using Wearable Accelerometers}, journal = {Sensors}, volume = {20}, year = {2020}, number = {20}, article-number = {5817}, url = {https://www.mdpi.com/1424-8220/20/20/5817}, pubmedid = {33066691}, issn = {1424-8220}, doi = {10.3390/s20205817}, }

ICCV

Person-in-WiFi: Fine-Grained Person Perception Using WiFi

Fei Wang, Sanping Zhou, Stanislav Panev, Jinsong Han, and Dong Huang

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2019

arXiv Bib HTML

@inproceedings{Wang_2019_ICCV,
  author = {Wang, Fei and Zhou, Sanping and Panev, Stanislav and Han, Jinsong and Huang, Dong},
  title = {Person-in-WiFi: Fine-Grained Person Perception Using WiFi},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = oct,
  year = {2019},
}

T-ITS

Road Curb Detection and Localization With Monocular Forward-View Vehicle Camera

Stanislav Panev, Francisco Vicente, Fernando De La Torre, and Véronique Prinet

IEEE Transactions on Intelligent Transportation Systems, 2019

DOI arXiv Bib HTML

@article{8532105,
  author = {Panev, Stanislav and Vicente, Francisco and De La Torre, Fernando and Prinet, Véronique},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  title = {Road Curb Detection and Localization With Monocular Forward-View Vehicle Camera},
  year = {2019},
  volume = {20},
  number = {9},
  pages = {3568-3584},
  keywords = {Three-dimensional displays;Cameras;Sensors;Laser radar;Image edge detection;Feature extraction;Roads;Curb detection;parking assistance;monocular camera;HOG;SVM;template fitting;tracking},
  doi = {10.1109/TITS.2018.2878652},
}