Gyeong-Moon Park

Secondary Motion-Aware 3D Clothed Gaussian Avatars from Monocular Videos

User-Controllable Dense Video Captioning: A Large-Scale Benchmark and Framework

Detecting Unknown Objects via Energy-based Separation for Open World Object Detection

Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time

MoRE: Mixture of Remapping Experts For Irreversible Feature-Level Unlearning

Audio-driven 3D Conversational Full-body Human Avatar Generation from a Single Image

VIDES: VIDEO EDITING IN SECONDS WITH ONE-STEP DIFFUSION MODELS

FedTAP: Federated Multi-Task Continual Learning via Dynamic Task-Aware Prototypes

Open-Set Domain Generalization for Semantic Segmentation

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series

Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech

Do Not Mimic My Voice: Teacher-Guided Unlearning for Zero-Shot Text-to-Speech

DDRL: A DIFFUSION-DRIVEN REINFORCEMENT LEARNING APPROACH FOR ENHANCED TSP SOLUTIONS

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series