Name: Yutong Song
Pronouns:
Institution: San Diego State university
Department: Computer Science
Biography:
I am now a second-year Ph.D. student in Computational Science in a joint program between San Diego State University and the University of California, Irvine. I have a broad interest in computational science, applied machine learning, network science, data analysis, security and privacy. My previous research field includes 3D computer vision, deep learning methods in engineering, wireless network optimization, smart pricing strategy, complex networks, and uncertain decision-making methods. My current research focuses on 3D hand pose estimation and mesh reconstruction based on deep learning methods.
Academic Status: PhD Student
Year in program: 2nd
Research Area/Department: Computer Science; Data Science; Machine Learning/AI
Other, specify:
Major/Specialty: My major is computational science and I have academic background in computer science and communication engineering. My previous research field includes 3D computer vision, deep learning methods in engineering, wireless network optimization, smart pricing strategy, complex networks, and uncertain decision-making methods. My current research focuses on 3D hand pose estimation and mesh reconstruction based on deep learning methods. In this project, we Reconstruct 3D interacting hand poses with minimal collisions from monocular single RGB images using a two-stage framework. The first stage adopts a convolutional neural network to generate coarse predictions, and the second stage retains the preciseness of 3D poses through the poison-based refinement module. I am very familiar with modeling and coding using Matlab and Python, as well as some machine learning packages and frameworks.
Degrees Earned or in Progress: Ph.D. student in Computational Science at University of California, Irvine & San Diego State University Feb (2022-present) B.E. in Communication Engineering at University of Electronic Science and Technology of China Sep (2016-Jun 2020)
What courses or academic preparation have you completed to prepare for a summer internship experience?
Some lectures I had in the past year are listed: Machine learning, scientific computing, image understanding, machine learning and data mining, programming in C++, and neural network & deep learning.
Have you published any research or worked on research/technical projects? Yes
Where has your research been published or where have you conducted research/technical projects? 1. Yutong Song, Krishna Murthy Kattiyan Ramamoorthy, WeiWang and Kazem Sohraby. A use-it-or-lose-it economic vcg auction approach for Noma wireless relay networks. In 2023 IEEE International Conference on Omni-layer Intelligent Systems (COINS), pages 1-6, 2023. 2. Yutong Song, Wei Wang, and Kazem Sohraby. Uberization of noma wireless network resource sharing: A driver-passenger game-theoretic approach. In 2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), pages 1-6. IEEE, 2022. (The Best Paper Award) 3. Jie Zhao,Yutong Song, Fan Liu, and Yong Deng. The identification of influential nodes based on structure similarity. Connection Science, Volume 33, pages 201-218. Taylor & Francis, 2021. 4. Jie Zhao, Yutong Song, and Yong Deng. A novel model to identify the influential nodes: Evidence theory centrality. IEEE Access, volume 8, pages 46773-46780. IEEE, 2020. 5. Yutong Song, and Yong Deng. Divergence measure of belief function and its application in data fusion. IEEE Access, volume 7, pages 107465-107472. IEEE, 2019.
Please describe your research/academic interests:
I have a broad interest in computational science, applied machine learning, network science, and data analysis. My previous research field includes 3D computer vision, deep learning methods in engineering, wireless network optimization, smart pricing strategy, complex networks, and uncertain decision-making methods. My current research focuses on 3D hand pose estimation and mesh reconstruction based on deep learning methods. For this summer internship, I hope that I can access some projects related to applied machine learning for engineering or some new scientific modeling methods.
Computational and Data Science Areas:
Computer Science; National Security; Data Analytics and Visualization; Machine Learning and AI
Research Synergy:
I am very interested in some projects listed on the DOE website and I find some of them are close to my current or previous research. One of them is Talita Perciano, Matthew Avaylon’s project “”Adaptable Deep Learning and Probabilistic Graphical Model System for Semantic Segmentation”” on the Berkley Lab website. They want to implement semantic segmentation algorithms based on deep learning methods. I am very familiar with deep learning models like CNN and U-net in their papers but for different tasks (human-pose estimation). Moreover, I am very interested in utilizing the Probabilistic Graphical Model for computer vision tasks. In this case, I think we can collaborate together for this project to explore more interesting tasks with machine learning methods.
Motivation:
I have a background in exploring networking and communication during my undergraduate studies. However, over the past year, I’ve developed a keen interest in applied machine learning methods, particularly deep learning. I’ve observed how large language models have significantly impacted our lives, and I believe that machine learning can greatly enhance researchers’ ability to solve problems effectively. I’m eager to learn more about how machine learning and applied mathematical modeling methods are applied in real engineering projects and everyday life. Additionally, I’m enthusiastic about actively participating in these exciting projects to gain practical experience. Furthermore, I aspire to connect with more researchers in the field and foster collaborations in the future. I understand the importance of networking and engaging with professionals to further my knowledge and contribute to innovative projects in the realm of machine learning and applied mathematics.
Lightning Talk Title: Data magic in 3D vision and network