← Search

Hyunwook Choi

2 accepted papers

2026

MATRIX: Mask Track Alignment for Interaction-aware Video Generation

ICLR 2026poster

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and mul…

Cited by 0SourcecodeScholar
2025

S4M: Boosting Semi-Supervised Instance Segmentation with SAM

ICCV 2025poster

Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to unreliable pseudo-label quality stemming from limited label…

Cited by 0SourcePDFScholar