CV
Rosaura G. VidalMata's Curriculum Vitae
Contact Information
| Name | Rosaura G. VidalMata |
| Professional Title | Research Scientist | Computer Vision |
| rosauravidal@gmail.com | |
| Phone | 872-202-8769 |
| Location | Morrisville, NC |
Professional Summary
Computer vision researcher with a Ph.D. in Computer Science and Engineering. Specializes in camera pipelines, edge model optimization, and visual recognition under severe constraints. Deploys real-time neural perception in PyTorch and C++ across mobile and PC platforms, with first-author papers in venues including IEEE TPAMI and WACV.
Experience
-
2022 - Present Morrisville, NC
AI Researcher
Lenovo Research
- Led cross-functional technical delivery of a dual-camera video pipeline showcased at NVIDIA GTC 2026, adapting stereo foundation models for hybrid edge-cloud execution to accelerate throughput from 0.89 FPS to 27 FPS (30× faster).
- Engineered an on-device document perception framework in C++, curating 52,216 multi-source images to increase AP75 by 30% over baseline and unifying camera and microphone modules into a shared low-latency runtime.
- Optimized a mobile low-light model for Motorola Edge via TFLite using FP16 quantization, layer pruning, and filter tuning, shrinking footprint from 1,554 MB to 1,198 MB (1.3× smaller) and runtime from 4.42 s to 1.89 s (2.3× faster) while meeting DXOMARK exposure and color benchmarks.
- Built an automated annotation and curation pipeline that raised throughput 40% and production output 130%, compiling and releasing the LENVIZ low-light benchmark (230,000+ frames; WACV 2026).
-
2016 - 2024 Notre Dame, IN
Doctoral Researcher, Computer Science and Engineering
University of Notre Dame
- Released UG2, a benchmark of 150,000+ aerial and ground video frames under weather, distance, and blur, reported in TPAMI and WACV (funded by IARPA and NVIDIA).
- Co-organized the CVPR 2018 and 2019 UG2+ prize challenges, evaluating 40 international algorithm submissions on video object recognition under sensor and weather degradation to publish foundational benchmarks in IEEE TPAMI and CVIU.
- Benchmarked 10 manipulation-localization methods and released an open-source detection toolkit under DARPA funding, designing a residual preprocessor with anomaly-enhancement loss and disparity augmentation for social-media compression.
-
2019 - 2019 Cambridge, MA
Graduate Research Intern
MIT-IBM Watson AI Lab
- Developed a joint visual-temporal embedding for unsupervised action segmentation in untrimmed video, gaining 4% mean-over-frames (MoF) over published state of the art on the Breakfast Actions dataset (published at WACV 2021).
- Won Best of Show at the IBM intern showcase, out of 50+ projects.
Education
-
2024 Notre Dame, IN
Ph.D.
University of Notre Dame
Computer Science and Engineering
- Dissertation: Rich Embedding Techniques to Improve Scene Understanding
-
2020 Notre Dame, IN
M.S.
University of Notre Dame
Computer Science and Engineering
-
2015 Morelos, Mexico
B.S.
Tecnológico de Monterrey
Computer Science and Engineering
- Excellence Scholarship
Awards
-
2026 Featured in 'Women in Computer Vision'
RSIP Vision WACV Daily
-
2023 Lenovo Research SVP Award of Individual Excellence
Lenovo Research
For computer vision research and delivery milestones
-
2019 Best of Show
IBM Intern Showcase
Won Best of Show out of 50+ intern projects
Service
- Panelist and poster-session moderator, CRA UR2PhD Workshop (New Orleans, 2026).
- Reviewer for CVPR, ICCV, WACV, ICPR, and ACCV (2019 – 2026).
- Guest lecture, Lehigh University (2022).
- Invited talk, Notre Dame CSE Graduate Research Seminar (2020).
- Mentor, Grace Hopper Celebration Research Scholars (2019).
- Organizer, UG2+ Prize Challenge Workshop, CVPR 2018 and CVPR 2019.
Skills
Research: On-device computer vision, Image enhancement, Stereo depth, Document detection, Video benchmarks
Programming Languages: Python, C++, C#, Java, MATLAB
Machine Learning: PyTorch, TensorFlow, Keras, TFLite, ONNX Runtime
Tools & Infrastructure: OpenCV, CMake, Docker, Git, Linux, Windows, Jira, Confluence
Cloud: AWS (EC2, S3)
Languages
Spanish : Native speaker
English : Fluent