1 code implementation • 27 Mar 2024 • Inhwan Bae, Young-Jae Park, Hae-Gon Jeon
In this paper, we propose SingularTrajectory, a diffusion-based universal trajectory prediction framework to reduce the performance gap across the five tasks.
1 code implementation • 27 Mar 2024 • Inhwan Bae, Junoh Lee, Hae-Gon Jeon
Next, to guide the language model in understanding and reasoning high-level knowledge, such as scene context and social relationships between pedestrians, we introduce an auxiliary multi-task question and answering.
1 code implementation • ICCV 2023 • Inhwan Bae, Jean Oh, Hae-Gon Jeon
In this paper, we present EigenTrajectory ($\mathbb{ET}$), a trajectory prediction approach that uses a novel trajectory descriptor to form a compact space, known here as $\mathbb{ET}$ space, in place of Euclidean space, for representing pedestrian movements.
2 code implementations • 20 Jul 2022 • Inhwan Bae, Jin-Hwi Park, Hae-Gon Jeon
A key idea of GP-Graph is to model both individual-wise and group-wise relations as graph representations.
1 code implementation • CVPR 2022 • Inhwan Bae, Jin-Hwi Park, Hae-Gon Jeon
Capturing multimodal natures is essential for stochastic pedestrian trajectory prediction, to infer a finite set of future trajectories.