Hello There!

  • Full Name:Rosaura G. VidalMata
  • Pronunciation: roh-SAH-ruh vee-DAL
  • Email:rvidalma@nd.edu
  • Website:www.rvidal.me
  • Research Interests:Computer Vision, Machine Learning, Image Enhancement, nd Biometrics.
I am a highly accomplished AI and Computer Vision expert with a deep passion for image enhancement, scene understanding, and deep learning. I have a track record of pushing the boundaries of research and delivering innovative solutions.
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.

[Experience] [Publications] [Research Projects] [CV]

My Resume

  • Education

  • Ph.D. in Computer Science and Engineering

    University of Notre Dame - 2016 - 2023

    Thesis topic: "Rich Embedding Techniques to Improve Scene Understanding"

    Advisors:Kevin W. Bowyer, Walter J. Scheirer. GPA: 3.95

  • Bachelor of Science in Computer Science and Engineering

    Tecnológico de Monterrey - Dec. 2015

    Honorable Mention for Excellence. GPA: 4.0

  • International Summer Undergraduate Research Experience Program

    University of Notre Dame - Summer 2015

    Worked on a research program between the University of Notre Dame and the WVU FBI/Biometric Center of Excellence.

    Research Project: Automatic classification of the eye’s orientation.


  • Work Experience

  • Mobile AI Researcher

    Lenovo Research - April 2022 - Present

    • Conducted research in low-light image enhancement, including data collection, analysis, and interpretation.
    • Collaborated with a team of researchers to design and implement experiments, analyze results, and identify areas for future research.
    • Developed and implemented innovative solutions using computer vision algorithms and deep learning frameworks for real-time applications on resource-constrained mobile devices.
    • Led the design and development of a robust data annotation and processing tool, streamlining the management and organization of over 6,000 data points, resulting in increased efficiency and accuracy.
    • Received the prestigious Lenovo Research SVP Award of Individual Excellence for outstanding contributions and exceptional research achievements.

  • Machine Learning Intern

    Perceptive Automata - Jun - Aug 2020

    • Contributed to a research project focused on improving person re-identification in low-resolution scenarios.
    • Conducted extensive experimentation and testing to evaluate the effectiveness of different approaches and identify areas for improvement.

  • Graduate Research Intern

    MIT-IBM Watson AI Lab - Jun - Aug 2019

    Designed a joint visual-temporal embedding method to improve the performance of temporal action segmentation (6% improvement over the state-of-the-art in the Breakfast Actions Dataset). Presented the results of my research project in the IBM Intern Showcase and got the "Best of Show" award.

  • Software Engineer

    Thermo Fisher Scientific - Jan - May 2016

    Designed and programmed web applications using Amazon Web Services. Worked applying SCRUM Agile Methodology to specify, develop and deliver products within restrictive timelines.

  • Google Student Ambassador

    Google Student Ambassador Program - 2014 - 2015

    Liaison between the Tecnológico de Monterrey, Campus Cuernavaca and Google. Directed group activities and coached over a thousand students in the use of Google Apps and Android Programming.

  • Software Specialist

    Enterprise Management Service - 2014 - 2015

    Designed, developed and maintained web applications and SCADA systems. Worked with a multidisciplinary team to convert business needs into technical specifications and provided counsel in the use and suitability of IT services.

Publications

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).

[pdf] [dataset] [2019 Workshop]


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).

[pdf] [Workshop]


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)

[pdf] [presentation]


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.

[pdf] [dataset] [2018 Workshop]


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.

[pdf] [dataset][presentation]


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

[pdf]

Research Projects

Fall 2021 - Present

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.

2020 - 2021

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.

2019 - 2020

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.

2016 - 2019

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.

Fall 2015

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:

  1. Feature engineering, using hand-crafted features classified by a support vector machine (SVM)
  2. Feature learning, using data-driven features learned and classified by a convolutional neural network (CNN)

Do you want to know more?

Email me!