Gyeong-Moon Park

Assistant Professor, Korea University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

2 papers

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition

#1010 Spotlight · Jongseo Lee, Wooil Lee, Gyeong-Moon Park, Seong Tae Kim, Jinwoo Choi

We propose DANCE, a novel explainable video action recognition framework that provides clear and structured explanations by disentangling motion dynamics and spatial context concepts.

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

#1211 · Tae-Young Lee, Juwon Seo, Jong Hwan Ko, Gyeong-Moon Park

We prevent unauthorized personalization of diffusion models at the model level.