Hello There!
- Full Name:Rosaura G. VidalMata
- Pronunciation: roh-SAH-ruh vee-DAL
- Email:rosauravidal@gmail.com
- Website:www.rvidal.me
- Research Interests:Computer Vision, Machine Learning, Image Enhancement, and Biometrics.
My expertise spans low-light image enhancement, object detection, and temporal action segmentation. I thrive on solving complex challenges in real-time applications on resource-constrained devices, constantly striving for optimal performance. Actively engaged in the research community, I regularly publish my work in top conferences, staying up-to-date with the latest advancements and contributing to the collective knowledge in AI and Computer Vision. I bring a driven and analytical approach to problem-solving, complemented by excellent communication skills.
My Resume
-
Education
-
Ph.D. in Computer Science and Engineering
University of Notre Dame - 2024Thesis topic: "Rich Embedding Techniques to Improve Scene Understanding"
Advisors:Kevin W. Bowyer, Walter J. Scheirer. GPA: 3.95
-
M.S. in Computer Science and Engineering
University of Notre Dame - 2020GPA: 3.95
-
Bachelor of Science in Computer Science and Engineering
Tecnologico de Monterrey - 2015Excellence Scholarship. GPA: 4.0
-
International Undergraduate Research Experience Program
University of Notre Dame - Summer 2015Worked on a research program between the University of Notre Dame and the WVU FBI/Biometric Center of Excellence.
Research Project: Eye orientation classification.
-
Work Experience
-
AI Researcher
Lenovo Research - 2022 - Present- Engineered a hybrid cloud/local background segmentation pipeline (14 FPS), reducing inference latency by 92% (300ms to 24ms).
- Led model development and architecture optimization for a GenAI face editing PoC.
- Architected AI camera solutions, cutting memory by 23% and runtime by 58%.
- Built a Python data annotation tool, streamlining 6,000+ data points and increasing throughput by 40%.
- Won the Lenovo Research SVP Award of Individual Excellence.
- Standardized dataset collection and annotator feedback, boosting production output by 130%.
- Developed an AI image alignment module, reducing runtime by 57% for mobile applications.
-
Graduate Research Intern
MIT-IBM Watson AI Lab - June - August 2019Designed a joint visual-temporal embedding method for temporal action segmentation (4% SOTA improvement). Won "Best of Show" at the IBM Intern Showcase.
-
Software Engineer
Thermo Fisher Scientific - January - May 2015Developed AWS-based web applications. Applied Agile/SCRUM methodologies to collaboratively deliver products within strict timelines.
Publications
M. Aithal, R. G. VidalMata, M. Kartha, G. Chen, E. Adhikarla, L. N. Kirsten, Z. Fu, N. A. Madhusudhana, J. Nasti, "LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset," in 2026 IEEE Winter Conference on Applications of Computer Vision (WACV).
S. Banerjee*, R. G. VidalMata*, Z. Wang, and W. J. Scheirer, "Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms," in Computer Vision and Image Understanding (CVIU).
S. Abraham, Z. Carmichael, S. Banerjee, R. VidalMata, A. Agrawal, M. N. A. Islam, W. Scheirer, and J. ClelandHuang, "Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems," in 2021 Workshop on AI Engineering (WAIN).
R. G. VidalMata, W. J. Scheirer, A. Kukleva, D. D. Cox, and H. Kuehne, "Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences," in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
R. G. VidalMata, [et. al.], "Bridging the Gap Between Computational Photography and Visual Recognition," in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), doi: 10.1109/TPAMI.2020.2996538.
R. G. VidalMata, S. Banerjee, W. J. Scheirer, K. Grm, and V. Struc, "UG^2: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition," in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1597-1606, March 2018. doi 10.1109.
A. Czajka, K. W. Bowyer, M. Krumdick, and R. G. VidalMata, "Recognition of Image-Orientation-Based Iris Spoofing," in IEEE Transactions on Information Forensics and Security, vol. 12, no. 9, pp. 2184-2196, Sept. 2017. doi: 10.1109/TIFS.2017.2701332
Research Projects
Disparity Augmentation for Manipulation Detection
Manipulation detection algorithms often rely on identifying local anomalies, where manipulated regions would be “sufficiently” different from the rest of the features in the image.
As part of this project we study techniques taken from computational photography as a way to exacerbate the anomalies present in manipulated regions to facilitate their detection by a variety of deep-learning and traditional manipulation detection methods.
Human-Drone Partnerships for Emergency Response Scenarios
The use of small Unmanned Aerial Vehicles to collect imagery in difficult or dangerous terrain offers clear advantages for time-critical tasks such as search-and-rescue missions, fire surveillance, and medical deliveries.
Employing a drone to search for a missing kayaker on a river or a child lost in the wilderness, survey a traffic accident or a forest fire, or to track a suspect in a school shooting would not only reduce risk to first responders but also allow for a wide-scale search to be deployed in an expedited manner.
Unsupervised Temporal Segmentation of Actions
Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long video data, but annotating such data is very time consuming and can not easily be automated or scaled.
To address this problem, we propose an approach that is able to provide a meaningful visual and temporal embedding out of the visual cues present in contiguous video frames.
Image Restoration and Enhancement for Visual Recognition
Can the application of enhancement algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content?
While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks.
Iris Image Orientation Recognition
Matching the iris codes from the left and right eyes of the same person gives a result that is on average basically the same as matching iris codes from unrelated persons.
Two approaches are compared on the same data, using the same evaluation protocol:
- Feature engineering, using hand-crafted features classified by a support vector machine (SVM)
- Feature learning, using data-driven features learned and classified by a convolutional neural network (CNN)