Video Moment Retrieval and Highlight Detection Using Captions Generated by Multimodal Large Language Models

Codebook-NeRF: Improving NeRF resolution based on codebookVideo Moment Retrieval and Highlight Detection       Using Captions Generated by Multimodal Large Language Models

Study For Automatic Pedestrian Data Augmented Learning Technique For Robust Multispectral Pedestrian Detection

Robust Video Moment Retrieval and Highlight Detection with Using Large Vision-Language Model

Robust 3D Object Detection Using 2D-Based Object Detection Information and Symmetry Knowledge

Efficient Sampling Method for Repetitive Data for Label Data Selection In Multispectral Pedestrian Detection

Effective Change Captioning via Feature Map Restoration in Noisy Environments

Handling Missing Modality Using Multimodal Relational Knowledge

Multimodal Deap Learning for Korean Fake News Detection

Multimodal Pedestrian Detection Using Attention and Multi Modal Guide

Single-Modal Pedestrian Detection Leveraging Multimodal Knowledge for Blackout Situations

Effective 3D Object Detection using 2D Object Detection information

Enhancing Multi-Modal Audio-Visual QA Model Performance via Single Modal Feature Maps with Added Noise input

Automatic Notification of Dangerous Situations in Blind Spots via Image-based Pedestrian Detection using Deep Learning