Sunghoon Im

AdaST: Adaptive Semantic Transformation of Visual Representation for Training-free Zero-shot Composed Image Retrieval

TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization

Temporal Grounding as a Learning Signal for Referring Video Object Segmentation

ADOR: Attention Dilution and Overlap Resolver for Complex Prompts in Text-to-Image Diffusion Models

Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining

Context-Aware Video Instance Segmentation

$\text{O}_\text{2}$VIS: Occupancy-aware Object Association for Temporally Consistent Video Instance Segmentation