Search Results for author: Inhwan Bae

Found 6 papers, 5 papers with code

Kinetic Typography Diffusion Model

no code implementations15 Jul 2024 Seonmi Park, Inhwan Bae, Seunghyun Shin, Hae-Gon Jeon

We apply the zero convolution to the text content, and impose it on the diffusion model.

SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model

1 code implementation CVPR 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.

Denoising Domain Adaptation +2

Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction

1 code implementation CVPR 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.

Image Captioning Language Modelling +3

EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting

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.

Human Dynamics Trajectory Forecasting

Non-Probability Sampling Network for Stochastic Human Trajectory Prediction

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.

Pedestrian Trajectory Prediction Trajectory Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.