Publications

* denotes equal contribution.

2026

HyFL-CLIP thumbnail

HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

Ji Ha Jang*, Hayeon Kim*, Chulwon Lee, Junghun James Kim, Se Young Chun

European Conference on Computer Vision (ECCV), 2026

ECCV Vision-Language

A hyperbolic fine-tuning framework that distills the well-established image-text alignment of Euclidean CLIP into hyperbolic space via cross-manifold similarity distillation.

Human Interaction-Aware 3D Reconstruction thumbnail

Human Interaction-Aware 3D Reconstruction from a Single Image

Gwanghyun Kim*, Junghun James Kim*, Suh Yoon Jeon*, Jason Park, Se Young Chun

Conference on Computer Vision and Pattern Recognition (CVPR), 2026  (Highlight)

CVPR Highlight Co-1st Author 3D Vision

A holistic framework for reconstructing physically plausible, high-fidelity textured 3D humans from a single image, explicitly modeling group- and instance-level cues to handle perspective distortion, occlusion, and inter-human interactions.

DiffBMP thumbnail

DiffBMP: Differentiable Rendering with Bitmap Primitives

Seongmin Hong*, Junghun James Kim*, Daehyeop Kim, Insoo Chung, Se Young Chun

Conference on Computer Vision and Pattern Recognition (CVPR), 2026

CVPR Co-1st Author Differentiable Rendering

A scalable differentiable renderer for bitmap primitives that optimizes thousands of elements via a highly parallelized custom CUDA pipeline, enabling practical image/video composition, layered export, and artist-friendly creative workflows.

UNCHA thumbnail

UNCHA: Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models

Hayeon Kim*, Ji Ha Jang*, Junghun James Kim, Se Young Chun

Conference on Computer Vision and Pattern Recognition (CVPR), 2026  (Highlight)

CVPR Highlight Vision-Language

An uncertainty-guided hyperbolic vision-language framework that models part-to-whole semantic representativeness via adaptive uncertainty, improving hierarchical compositional understanding and performance on zero-shot classification, retrieval, and multi-label classification.

2018

One-Shot Item Search thumbnail

One-Shot Item Search with Multimodal Data

Jonghwa Yim, Junghun James Kim, Daekyu Shin

arXiv preprint, 2018

Preprint Multimodal Retrieval

A multimodal item retrieval method that jointly searches over image and text features rather than handling them separately, improving similar-item search on large-scale shopping datasets with only minimal additional computational overhead.