papers

Publications (11)

cs.CV2026

ComPose: When to Trust Hands for Object Pose Tracking

Jisu Shin, Junoh Lee, JunGyu Lee +5

Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they…

cs.CL2024

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

Inhwan Bae, Junoh Lee, Hae-Gon Jeon

Language models have demonstrated impressive ability in context understanding and generative performance. Inspired by the recent success of language foundation models, in this pape…

cs.CV2024

SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model

Inhwan Bae, Young-Jae Park, Hae-Gon Jeon

There are five types of trajectory prediction tasks: deterministic, stochastic, domain adaptation, momentary observation, and few-shot. These associated tasks are defined by variou…

cs.CV2025

Continuous Locomotive Crowd Behavior Generation

Inhwan Bae, Junoh Lee, Hae-Gon Jeon

Modeling and reproducing crowd behaviors are important in various domains including psychology, robotics, transport engineering and virtual environments. Conventional methods have…

cs.CV2023

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

Inhwan Bae, Jean Oh, Hae-Gon Jeon

Capturing high-dimensional social interactions and feasible futures is essential for predicting trajectories. To address this complex nature, several attempts have been devoted to…

cs.CV2022

Non-Probability Sampling Network for Stochastic Human Trajectory Prediction

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. The inferred trajectories are based on obse…

cs.CV2026

Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting

Junoh Lee, Junmyeong Lee, Yeon-Ji Song +4

The reconstruction of dynamic 3D scenes using 3D Gaussian Splatting has shown significant promise. A key challenge, however, remains in modeling realistic motion, as most methods f…

cs.CV2022

Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction

Inhwan Bae, Jin-Hwi Park, Hae-Gon Jeon

Modeling the dynamics of people walking is a problem of long-standing interest in computer vision. Many previous works involving pedestrian trajectory prediction define a particula…

cs.CV2024

Kinetic Typography Diffusion Model

Seonmi Park, Inhwan Bae, Seunghyun Shin +1

This paper introduces a method for realistic kinetic typography that generates user-preferred animatable 'text content'. We draw on recent advances in guided video diffusion models…

cs.CV2024

Fully Explicit Dynamic Gaussian Splatting

Junoh Lee, Chang-Yeon Won, Hyunjun Jung +2

3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of t…

cs.HC2026

Identifying a Level-up Pathway for AI-assisted Counterspeech through Elaboration

Han Li, Inhwan Bae, Natalie Bazarova +1

The paper evaluates three AI‑assisted writing systems that help ordinary social‑media users craft counterspeech against vaccine‑skeptical posts, finding that AI support—especially…

#counterspeech#vaccine misinformation#ai-assisted writing#social media