Youngwan Lee

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents

arXiv 2026

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding

CVPR 2025 1

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

arXiv 2022

CenterMask : Real-Time Anchor-Free Instance Segmentation

centermask-real-time-anchor-free-instance

Sung Ju Hwang

Kangsan Kim

Woongyeong Yeo

Geon Park

Jaehong Yoon

Jongyoul Park

Mengye Ren

Suji Kim

Sunil Hwang

Yanlai Yang