Junho Kim

6

Papers

15

Total Citations

Papers (6)

Fully Geometric Panoramic Localization

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis

StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance

Learning 3D Scene Analogies with Neural Contextual Scene Maps

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

Enhancing Creative Generation on Stable Diffusion-based Models