Focus

Research Interests

3D Vision

Learning geometric representations that recover and reason about the structure of objects and scenes in three-dimensional space.

Geometry3D RepresentationScene Understanding

3D Object Detection

Detecting and localizing objects in 3D by modeling spatial context, depth uncertainty, and multi-view visual evidence.

Camera-only 3D DetectionDepth ReasoningMulti-view Perception

Multimodal Learning

Combining visual, geometric, and semantic modalities to build more robust and generalizable perception systems.

Cross-modal FusionVision-LanguageRepresentation Learning

Updates

News

Research Output

Publications

Journal publication and research output.

Visual placeholder for A Method for Reducing False Negative Rate in Non-Maximum Suppression of YOLO Using Bounding Box Density JMIS 2023

A Method for Reducing False Negative Rate in Non-Maximum Suppression of YOLO Using Bounding Box Density

Dong-Hyeon Jeon, Tae-Sung Kim, and Jin-Sung Kim

Journal of Multimedia Information System, 10(4), 293–300, 2023

Paper

Background

Education

M.S. Student

Kyung Hee University

Department of Artificial Intelligence · Visual Science Lab