Kyonggi University Artificial Intelligence Laboratory
Hyelim Bae, Incheol Kim, “Open-vocabulary 3D Semantic Segmentation With 3D Region Mask Proposal and 2D-3D Visual Feature Ensemble”, 2024
Junghyeon Choi, Incheol Kim, “Goal Object Grounding and Multimodal Mapping for Multi-object Visual Navigation”, 2024
Sungho Song, Incheol Kim, “Transformer-based 3D Instance Segmentation With Auxiliary Denoising Learning”, 2023
Hyunjin Chun, Incheol Kim, “Dynamic Anchor Box-based Instance Decoding and Position-aware Instance Association for Online Video Instance Segmentation”, 2023
Hyelim Bae, Incheol Kim, “3D Semantic Scene Segmentation with Multi-View RGB-D Images in Indoor Environments”, 2023
Hojun Baek, Incheol Kim,"Knowledge-based 3D Scene Graph Generation from Point Clouds", 2023
Hyunjin Chun, Incheol Kim, “Online Video Instance Segmentation with Dynamic Anchor Boxes”, 2023
Hyelim Bae, Incheol Kim, "Multi-Modal Cross Attention for 3D Point Cloud Semantic Segmentation", 2023
Jinhwan Kim, Junghyeon Choi, Incheol Kim, “Visual Context Embedding and Deadlock Processing for Target-driven Visual Navigation”, 2023
Hojun Baek, Incheol Kim, "Context-based 3D Scene Graph Generation from Indoor Point Clouds", 2022
Hyunjin Chun, Incheol Kim, “Human Instance Segmentation using Video Data Augmentation”, 2022
Minkyo Kang, Jinhwan Kim, Junghyeon Choi, Incheol Kim, “Transformer-based On-Offline Hybrid Reinforcement Learning for Locomotion Tasks”, 2022
Hyelim Bae, Hojun Baek, Incheol Kim, “3D Point Cloud Semantic Segmentation Using Multi-View Color Images”, 2022
Sungho Song, Incheol Kim, “Unseen Object Pose Estimation using a Monocular Depth Estimator”, 2022
Sangui Lee, Incheol Kim, “Graph Reasoning and Context Fusion for Multi-task, Multi-hop Question Answering”, 2021
Gayoung Jung, Incheol Kim, “Dynamic 3D Scene Graph Generation for Robotic Manipulation Tasks”, 2021
Seokjun Lee, Incheol Kim, "Constraint Satisfaction for Motion Feasibility Checking", 2021
Eunjin Jung, Incheol Kim, "Hybrid Imitation Learning Framework for Robotic Manipulation Tasks", 2021
Gayoung Jung, Jonghoon Lee, Incheol Kim, "Tracklet Pair Proposal and Context Reasoning for Video Scene Graph Generation", 2021
Jaeyun Lee, Incheol Kim, "Vision–Language–Knowledge Co-Embedding for Visual Commonsense Reasoning", 2021
Sujin Lee, Incheol Kim, "DVC-Net: A Deep Neural Network Model for Dense Video Captioning", 2021
Jisu Hwang, Incheol Kim, "Joint Multimodal Embedding and Backtracking Search in Vision-and-Language Navigation", 2021
Yeongsu Cho, Incheol Kim, "NMN-VD: A Neural Module Network for Visual Dialog", 2021
Gayoung Jung, Incheol Kim, "Multimodal Context Embedding for Scene Graph Generation", 2020
Kyuyeol Jung, Incheol Kim, “Continual Multiagent Reinforcement Learning in Dynamic Environments”, 2020
Jaeyun Lee, Incheol Kim, “Image-Language Co-embedding and Knowledge Graph Embedding for Visual Commonsense Reasoning”, 2020
Chang J. Nam, Seok J. Lee, Jeong H. Lee, Sang H. Cheong, Dong H. Kim, Chang W. Kim, In C. Kim, Sung K. Park, "A Software Architecture for Service Robots Manipulating Object in Human Environments", 2020
Gayoung Jung, Incheol Kim, “Scene Graph Generation with Graph Neural Network and Multimodal Context”, 2020
Eunjin Jung, Seokjun Lee, Incheol Kim, "AugGAIL: Augmented Generative Adversarial Imitation Learning for Robotic Manipulation Tasks", 2020
Giho Lee, Incheol Kim, "Open Domain Question Answering Based on Knowledge Graph", 2019
Jaeyun Lee, Incheol Kim, "Visual Commonsense Reasoning with Knowledge Graph", 2019
Yeongsu Cho, Incheol Kim, "Image Understanding for Visual Dialog", 2019
Donghyeop Shin, Incheol Kim, "Modelling Dynamics of Indoor Environment with 3D Scene Graphs", 2019
Yeongsu Cho, Incheol Kim, “Neural Module Networks for Visual Dialog”, 2019
Jisu Hwang, Incheol Kim, “Real-Time Visual Grounding for Natural Language Instructions with Deep Neural Network”, 2019
Seokjun Lee, Incheol Kim, "A Spatio-Temporal Context Query Processing Framework for Service Robots", 2019
Sujin Lee, Incheol Kim, "Dense Video Captioning with Semantic Features and Attention", 2018
Donghyeop Shin, Incheol Kim, "Deep Image Understanding Using Multilayered Contexts", 2018
Donghyeop Shin, Incheol Kim, "Scene Graph Generation by Exploring in Three-Dimensional Space", 2018
Seokjun Lee, Incheol Kim, "A Robotic Context Query-Processing Framework based on Spatio-Temporal Context Ontology", 2018
Yeongsu Cho, Jisu Hwang, Incheol Kim, "Deep Reinforcement Learning for Optimizing Visual Questions", 2018
Donghyeop Shin, Incheol Kim, "Using Contextual Information for Image Captioning and Scene Graph Generation", 2018
Eunjin Jung, Sangjoon Lee, Seokjun Lee, Incheol Kim, “Proximal Policy Optimization for Learning Robotic Manipulation Tasks”, 2018
Jaeyun Lee, Giho Lee, Incheol Kim, "Detecting Visual Attributes and Spatial Relationships with Deep Neural Networks", 2018
네이버에서 주최하는 AI 딥러닝 경진대회에서 3위 입상
Sujin Lee, Incheol Kim, "Multimodal Feature Learning for Video Captioning", 2018
Yeongtaek Song, Incheol Kim, "Video Activity Detection with Semantic Features and Temporal Region Proposals", 2017
Junbae Suh, Seokjun Lee, Incheol Kim, "Modeling Object and Their Affordances Semantically for Robot Manipulation Services", 2017
Sujin Lee, Incheol Kim, "Semantic Feature Learning and Selective Attention for Video Captioning", 2017
Donghyeop Shin, Incheol Kim, "Modeling Relationships between Objects for Referring Expression Comprehension", 2017
Seokjun Lee, Incheol Kim, "Generating Robot Task Plans from Action Ontology", 2017
Yeongtaek Song, Junbae Suh, Incheol Kim, "Learning Recurrent Neural Networks for Activity Detection from Untrimmed Videos", 2017
동일 실내 환경 내 서로 다른 방들에 있는 사람들에게 로봇이 돌아다니며 공지사항(예컨대, “점심 시간입니다”)을 전달하는 서비스 프로그램을 개발
지난 18일 ETRI(한국전자통신연구원)에서 연구원이 개발한 인공지능 프로그램 '엑소브레인'(Exobrain)과 인간 퀴즈왕과의 대결이 펼쳐졌다.
Jonghoon Kim, Seokjun Lee, Dongha Kim, Incheol Kim, "Dynamic Context Management and Spatio-Temporal Reasoning for Intelligent ServiceRobots", 2016