Paul Hongsuck Seo

6

Papers

38

Total Citations

Papers (6)

Learning Correlation Structures for Vision Transformers

Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation

Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression

DialNav: Multi-turn Dialog Navigation with a Remote Guide

Multi-Granularity Video Object Segmentation

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation