Keynotes
Laura Leal-Taixé
Senior Research Manager at NVIDIA and Adjunct Professor at the Technical University of Munich (TUM)
Title
Multiple object tracking with graphs - from classical to learned
Abstract
In this talk, I will present how graphs have been used in the literature for multiple object tracking. I will start with classical non-learned formulations until most recent state-of-the-art trackers based on graph neural networks.
Biography
Prof. Dr. Laura Leal-Taixé is a Senior Research Manager at NVIDIA and also an Adjunct Professor at the Technical University of Munich (TUM), leading the Dynamic Vision and Learning group. From 2018 until 2022, she was a tenure-track professor at TUM. Before that, she spent two years as a postdoctoral researcher at ETH Zurich, Switzerland, and a year as a senior postdoctoral researcher in the Computer Vision Group at the Technical University in Munich. She obtained her PhD from the Leibniz University of Hannover in Germany, spending a year as a visiting scholar at the University of Michigan, Ann Arbor, USA. She pursued B.Sc. and M.Sc. in Telecommunications Engineering at the Technical University of Catalonia (UPC) in her native city of Barcelona. She went to Boston, USA to do her Masters Thesis at Northeastern University with a fellowship from the Vodafone foundation. She is a recipient of the Sofja Kovalevskaja Award of 1.65 million euros in 2017, the Google Faculty Award in 2021, and the ERC Starting Grant in 2022.
Yifan Wang
Assistant Professor at the National University of Singapore
Title
Geometric structures and why (and how) to use them in deep models?
Abstract
In the last decades, the computer graphics community has invented many geometric structures to serve as useful representations to facilitate geometric modeling. As deep learning is transcending the 2D image space into the 3D realm through more efficient architectures, it may seem appealing to obsolete many previously developed geometric structures in exchange for more flexibility and generalizability. In this talk, I will convince you with several counter-examples why traditional geometric structures are valuable assets in the era of deep learning and how to leverage them to address typical shortcomings of neural networks in the context of geometry modeling.
Biography
Yifan is an incoming assistant professor at the National University of Singapore. Her area of research lies in applying machine learning techniques, especially deep learning, to challenging image and geometry processing problems. She’s currently a postdoc at the Computational Imaging Lab at Stanford University working with Professor Gordon Wetzstein, before that she obtained her PhD from the Interactive Geometry Lab at ETH Zurich under the supervision of Prof. Olga Sorkine-Hornung. She received Apple AI/ML fellowship in 2020, and the Swiss Postdoc Mobility fellowship in 2022. Her doctorate dissertation has been awarded the ETH Medal in 2022 and Best PhD Thesis at Eurographics in 2023.
Theodore Kim
Associate Professor of Computer Science at Yale University
Title
Is Synthetic Training Data A Bad Idea?
Abstract
Bias in real-world training data has received lots of attention, especially since the work of Buolamwini and Gebru. Removing this bias by using computer graphics algorithms to generate synthetic data has been posed as a potential solution, but comes with its own insidious prejudices. Even in these supposedly objective algorithms, in the words of media scholar Gaboury, “reality is unevenly distributed”. In this talk, I will discuss the unevenness of this distribution, where it comes from, and how it might impact deep learning in the future.
Biography
Theodore Kim is an Associate Professor in Computer Science at Yale University, where he investigates biomechanical solids, fluid dynamics, and topics in geometry. Previously, he was a Senior Research Scientist at Pixar Animation Studios. He received a PhD from the University of North Carolina in 2006, and a BS from Cornell University in 2001. He has received the NSF CAREER Award, multiple Best Paper awards, and two Scientific and Technical Academy Awards. His algorithms have appeared in over 20 films, and he has screen credits for Cars 3, Coco, Incredibles 2, and Toy Story 4.