Skip to main content

Alexis Amoyo
Florida State University
I am a rising senior completing my Bachelor's in Computer Science and Minor in Physics at Florida State University. The University of Central Florida's REU program in Computer Vision was a wonderful opportunity to learn more about the research process and explore Computer Vision through a research-oriented lens. This summer, I worked with Dr. Tanvir Ahmed on creating a Computer Vision System to Assess Building Damages After a Hurricane. Existing models utilize MobileNet, a lightweight architecture that uses depth-wise separable convolutions to classify building damages based on a masked image. After attempting to replicate these results through Transfer Learning on the datasets DoriaNet and MV-Harvey, which assessed building damages from Hurricane Dorian and Harvey, respectively, we experimented with different architectures to improve the performances of existing models. These architectures include ResNet, Visual Transformers, as well as CLIP. Further information about my project may be found below in the weekly presentations and report provided. If you have any questions, you can email me at alexisamoyo@gmail.com or Dr. Tanvir Ahmed at Tanvir.Ahmed@ucf.edu
Alejandro Aparcedo Gonzalez
University of Central Florida
I am a rising senior at the University of Central Florida majoring in Computer Science. I had already been introduced to Computer Vision from working on projects with AI@UCF. The REU program helped me solidify my skills in CV and gave me an extensive introduction to academic research. Over the summer, I worked with Dr. Ser-Nam Lim on the effect of Data augmentation on Visual LLM, more specifically LLaVA. To view my progress please refer to the weekly presentations below. If you have any further questions, please feel free to reach out to me at aaparcedo.io@gmail.com.
Akhil Arularasu
Emory University
Born and raised in Central New Jersey, Akhil is now a rising sophomore and Robert W. Woodruff Scholar at Emory University in Atlanta, Georgia. He is a Computer Science and Business Administration double major at Emory, having completed coursework in Data Structures & Algorithms, Mathematical Foundations of Computer Science, and Business Data & Decision Analytics thus far. Prior to the REU, Akhil has experience with Java, Python (and associated packages), HTML, Flask and more, but this REU experience has expanded his knowledge greatly on the Computer Vision and Deep Learning aspects of the field. This summer, Akhil is working with Dr. Gaurav Kumar Nayak, Parth Parag Kulkarni, and Dr. Mubarak Shah on Robust Image Geolocalization. Existing research has explored usage of Transformers for Cross-View Image Geolocalization with the TransGeo model on the CVUSA dataset. This summer, Akhil will be working to develop a new, improved model that can also process noisy data and improve the performance of geolocalization techniques in this territory. For more details on his project and progress, please refer to his weekly presentations, report, and poster below. Please feel free to contact him at helloakhil@gmail.com or at akhil.arularasu@emory.edu!
Philomina Ekezie
Mercer University
Hello hello!! My name is Philomina Ekezie. I am a rising junior at Mercer University in Georgia where I will continue to pursue my Bachelor of Science in Computer Science this upcoming fall semester. I am more than grateful and extremely ecstatic to be participating in such a prestigious Computer Vision research program at the lovely UCF. Prior to starting this program, a majority of my skills and expertise were in software development and basic coding, so I did not have much experience with Artificial Intelligence and Machine Learning. However, I found these fields to be extremely fascinating and interesting, so this internship was the perfect opportunity for to dive in and learn as much as I could about such significant topics within the world of Computer Research. During the internship, I worked with Nyle Siddiqui to simultaneously identify a subject and the action performed by the subject in video sequences.
Sarah Fleischer
University of Central Florida
I'm a rising senior at the University of Central Florida, majoring in Mechanical Engineering. I had a general idea of Computer Vision prior to this REU (as it was covered in my Intro to Robotics class), but I gained hands on experience through my research and assignments. My interest in Computer Vision stemmed from its applications in robotics, as Robot Vision is revolutionizing the industry. I am currently working on an action recognition model under my mentor Jyuti Kini that identifies human actions using RGB, Depth, and Gaze through videos in the Meccano dataset. We will be improving upon the base code provided for the ICIAP Competition, utilizing the SlowFast network to capture spatial and temporal information by analyzing the frames through both slow and fast pathways. We will be changing the base code from a convolutional neural network to a transformer based network to improve accuracy and efficiency.
Ethan Frakes
University of Central Florida
I am a rising junior majoring in Computer Science here at the University of Central Florida. I had some prior experience with Artificial Intelligence prior to the summer through the course Algorithms for Machine Learning and AI@UCF, and some small experience with Computer Vision, also in Algorithms for Machine Learning. However, this REU has given me an incredible opportunity by rapidly broadening my knowledge of more low-level CV and AI concepts such as Convolutional Neural Networks, Transformers, and Diffusion. Over this summer, I will be working with Dr. Chen Chen on Video Content Generation using Diffusion models. Because novel Text-to-Video (T2V) models require large video datasets to train and are as of now inefficient for mass-deployment, we will be experimenting by fine-tuning pre-trained Text-to-Image (T2I) models such as Stable Diffusion for one-shot video editing and zero-shot novel video generation. To view my progress, you can refer to the weekly presentations below or if you would like to correspond, you can reach me at et250818@ucf.edu.
Gustavo Garcia
Ana G. Mendez University (Gurabo Campus)
I am a senior at Ana G. Mendez University (Gurabo Campus), majoring in computer engineering. While I’ve had experience in some computer science courses and topics, this summer has been my first introduction to the fields of computer vision and machine learning. Thus, this REU has significantly increased my understanding of computer vision by offering a short course on its fundamentals and giving me the opportunity to work with assistant professor Dr. Mengjie Li on a graduate-level research project. With the assistance of my mentor, I will work to develop a deep learning-based algorithm for the segmentation of photovoltaic (PV) modules from satellite and aerial imagery of different types of PVs. For information about my progress, check out my weekly presentations on https://www.crcv.ucf.edu/nsf-projects/reu/reu-2023/.
Nathan Labiosa
University of Wisconsin - Madison
Hello! I am a rising junior studying biomedical engineering and computer science at the University of Wisconsin - Madison. I’ve been exposed to computer vision in previous classes, including topics in neural networks, linear algebra in machine learning, and general AI principles. I am very excited to continue learning about this field and the opportunity to work with Dr. Lim. This summer, I will be working on Distilling Multi-Modal Large Language Models. If you have any questions, you can contact me at nathan.labiosa@gmail.com.
Sabrina Lopez
University of Central Florida
I am a rising senior at the University of Central Florida, majoring in Computer Science. I am interested in computer vision, machine learning, and artificial intelligence. Through the REU program, I am excited to learn and develop my skills in computer vision as well as engage myself with a cutting-edge and interesting research project. This summer, I am working with Gaurav Nayak and Dr. Shah on creating a program that can perform dataset condensation on videos. The goal of the project is, with the smaller synthetic dataset, to produce similar video classification accuracy results in comparison to the results of when videos are classified with the original dataset. Our approach involves intertwining code for dataset condensation with distribution matching with code that transforms videos into super images. For more detailed information, refer to my presentations, report, and poster. You can also email me at sabrinameganlopez015@gmail.com.
Misaki Matsuura
Case Western Reserve University
I am a rising junior at Case Western Reserve University majoring in Data Science and Analytics and minoring in Economics. I have done some computer science research prior to this program, but this is my first exposure to the field of computer vision so I am very excited for this learning opportunity. I am working with Dr. Ser Nam Lim on evaluating different state-of-the-art visual large language models on their performance with zero-shot classification. I will be focusing on the CLIP model developed by OpenAI and a more recent multimodal model called LLaVA. To view my progress in detail, please feel free to check out my weekly presentations and reach out to me at misaki.matsuura@knights.ucf.edu with any questions.