Publications

Seokha Moon, Janghyun Baek, Giseop Kim, Jinkyu Kim, Sunwook Choi (2025). Mitigating Trade-off: Stream and Query-guided Aggregation for Efficient and Effective 3D Occupancy Prediction. In ArXiv.

PDF Cite

Minjeong Park, Hongbeen Park, Jinkyu Kim (2025). VITA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute Recognition. In ICIP2025.

PDF Cite Code

Edward Kim, Devan Shanker, Varun Bharadwaj, Hongbeen Park, Jinkyu Kim, Hazem Torfah, Daniel Fremont, Sanjit Seshia (2025). Querying Labeled Time Series Data with Scenario Programs. In NASA Formal Methods.

PDF Cite

Gyeongrok Oh, Sungjune Kim, Heeju Ko, Hyung-gun Chi, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sungjoon Choi, Sujin Jang, Sangpil Kim (2025). 3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation. In CVPR2025.

PDF Cite

Sungsik Kim, Janghyun Baek, Jinkyu Kim, Jaekoo Lee (2025). GUIDE-CoT: Goal-driven and user-informed dynamic estimation for pedestrian trajectory using chain-of-thought. In AAMAS2025.

PDF Cite Code

Daewon Chae, June Suk Choi, Jinkyu Kim, Kimin Lee (2025). DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models. In AAAI2025.

PDF Cite

Minseung Lee, Seokha Moon, Seung Joon Lee, Jinkyu Kim (2024). Sparse-to-Dense LiDAR Point Generation by LiDAR-Camera Fusion for 3D Object Detection. In ArXiv.

PDF Cite

Daewon Chae, Nokyung Park, Jinkyu Kim, Kimin Lee (2024). InstructBooth: Instruction-following Personalized Text-to-Image Generation. In ArXiv.

PDF Cite Project

Ethan Ewer, Daewon Chae, Thomas Zeng, Jinkyu Kim, Kangwook Lee (2024). ENTP: Encoder-only Next Token Prediction. In ArXiv.

PDF Cite

Gyusam Chang, Jiwon Lee, Donghyun Kim, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sujin Jang, Sangpil Kim (2024). Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection. In NeurIPS 2024.

PDF Cite

Mincheol Chang, Siyeong Lee, Jinkyu Kim, Namil Kim (2024). Just Add $100 More, Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem. In NeurIPS 2024.

PDF Cite

Yechan Kang, Mingyeong Seo, Jeonghee Jo, Hyun Jae Jang, Jongkil Park, Jaewook Kim, Suyoun Lee, Jinkyu Kim, Seongsik Park (2024). H-Direct: Homeostasis-aware Direct Spike Encoding for Deep Spiking Neural Networks. In NeurIPS Workshop 2024.

Cite

Seokha Moon, Kyuhwan Yeon, Hayoung Kim, Seong-Gyun Jeong, Jinkyu Kim (2024). Who Should Have Been Focused: Transferring Attention-based Knowledge from Future Observations for Trajectory Prediction. In ICPR 2024.

Cite

Seongbeom Park, Haeji Jung, Daewon Chae, Hyunju Yun, Sungyoon Kim, Suhong Moon, Jinkyu Kim, Seunghyun Park (2024). Text-Driven Prototype Learning for Few-Shot Class-Incremental Learning. In ICPR 2024.

Cite

Nokyung Park, Daewon Chae, Jeongyong Shim, Sangpil Kim, Eun-sol Kim, Jinkyu Kim (2024). Bridging the Domain Gap by Clustering-based Image-Text Graph Matching. In ICPR 2024.

PDF Cite

Jungmin Ha, Euihyun Yoon, Sungsik Kim, Jinkyu Kim, Jaekoo Lee (2024). Leveraging Inductive Bias in ViT for Medical Image Diagnosis. In BMVC 2024.

Cite

Jimin Sohn, Haeji Jung, Alex Cheng, Jooeon Kang, Yilin Du, David R Mortensen (2024). Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages. In EMLNP 2024.

Cite

Haeji Jung, Changdae Oh, Jooeon Kang, Jimin Sohn, Kyungwoo Song, Jinkyu Kim, David R. Mortensen (2024). Mitigating the Linguistic Gap with Phonemic Representations for Robust Multilingual Language Understanding. In EMLNP 2024 Workshop.

PDF Cite Project

Jiyun Jang, Mincheol Chang, Jongwon Park, Jinkyu Kim (2024). Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps. In IROS 2024.

PDF Cite

Seokha Moon, Hyun Woo, Hongbeen Park, Haeji Jung, Reza Mahjourian, Hyung-gun Chi, Hyerin Lim, Sangpil Kim, Jinkyu Kim (2024). VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions. In ECCV 2024.

PDF Cite

Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, Sangpil Kim (2024). MEVG Multi-event Video Generation with Text-to-Video Models. In ECCV 2024.

PDF Cite

Hongbeen Park, Minjeong Park, Giljoo Nam, Jinkyu Kim (2024). LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System. In ECCV 2024.

PDF Cite

Sungjune Kim, Hadam Baek, Seunggwan Lee, Hyung-gun Chi, Hyerin Lim, Jinkyu Kim, Sangpil Kim (2024). Enhanced Motion Forecasting with Visual Relation Reasoning. In ECCV 2024.

PDF Cite Video

Seokha Moon, Hongbeen Park, Jungphil Kwon, Jaekoo Lee, Jinkyu Kim (2024). Learning Temporal Cues by Predicting Objects Move for Multi-camera 3D Object Detection. In ICRA 2024.

Cite

Seung Hyun Lee, Hyung-gun Chi, Gyeongrok Oh, Wonmin Byeon, Sang Ho Yoon, Hyunje Park, Wonjun Cho, Jinkyu Kim, Sangpil Kim (2024). Robust Sound-guided Image Manipulation. In Neural Networks.

PDF Cite Project

Sungjune Kim, Hyung-gun Chi, Hyerin Lim, Karthik Ramani, Jinkyu Kim, Sangpil Kim (2024). Higher-order Relational Reasoning for Pedestrian Trajectory Prediction. In CVPR 2024.

Cite

Jinbae Im, Jeongyeon Nam, Nokyung Park, Hyungmin Lee, Seunghyun Park (2024). EGTR: Extracting Graph from Transformer for Scene Graph Generation. In CVPR 2024.

PDF Cite

Gyusam Chang, Wonseok Roh, Sujin Jang, Dongwook Lee, Daehyun Ji, Gyeongrok Oh, Jinsun Park, Jinkyu Kim, Sangpil Kim (2024). CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-based 3D Object Detection. In AAAI2024.

PDF Cite

Seongbeom Park, Suhong Moon, Seunghyun Park, Jinkyu Kim (2024). Localization and Manipulation of Immoral Visual Cues for Safe Text-to-Image Generation. In WACV2024.

PDF Cite

Mincheol Chang, Seokha Moon, Reza Mahjourian, Jinkyu Kim (2024). BEVMap: Map-Aware BEV Modeling for 3D Perception. In WACV2024.

PDF Cite Video

Geewook Kim, Hodong Lee, Daehee Kim, Haeji Jung, Sanghee Park, Yoonsik Kim, Sangdoo Yun, Taeho Kil, Bado Lee, Seunghyun Park (2023). Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models. In EMNLP 2023.

PDF Cite Video

MyungHak Lee, Wooseong Cho, Sungsik Kim, Jinkyu Kim, Jaekoo Lee (2023). Distillation for High-Quality Knowledge Extraction via Explainable Oracle Approach. In BMVC2023.

PDF Cite Code

Yujin Jeong, Wonjeong Ryoo, Seunghyun Lee, Dabin Seo, Wonmin Byeon, Sangpil Kim, Jinkyu Kim (2023). The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion. In ICCV2023.

PDF Cite Code Project

Yujin Jeong, Wonjeong Ryoo, Seunghyun Lee, Dabin Seo, Wonmin Byeon, Sangpil Kim, Jinkyu Kim (2023). The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion. In ICMLW2023.

PDF Cite Code Project

Seongbeom Park, Suhong Moon, Seunghyun Park, Jinkyu Kim (2023). Localization and Manipulation of Immoral Visual Cues for Safe Text-to-Image Generation. In ICMLW 2023.

PDF Cite

Nokyung Park, Daewon Chae, Jeongyong Shim, Sangpil Kim, Eun-sol Kim, Jinkyu Kim (2023). Bridging the Domain Gap by Clustering-based Image-Text Graph Matching. In ICMLW 2023.

PDF Cite

Seokha Moon, Sejeong Lee, Hyun Woo, Kyuhwan Yeon, Hayoung Kim, Seong-Gyun Jeong, Jinkyu Kim (2023). RUFI: Reducing Uncertainty in Behavior Prediction with Future Information. In CVPRW2023.

PDF Cite

Yongrae Kim, Hyungmin Gwak, Jaehoon Oh, Minho Kang, Jinkyu Kim, Hyun Kwon, Sunghwan Kim (2023). CloudNet: A LiDAR-Based Face Anti-Spoofing Model That Is Robust Against Light Variation. In IEEE Access.

PDF Cite

Suhong Moon, Domas Buracas, Seunghyun Park, Jinkyu Kim, John Canny (2023). An Embedding-Dynamic Approach to Self-supervised Learning. In WACV 2023.

PDF Cite

Daeun Lee, Jongwon Park, Jinkyu Kim (2022). Resolving Class Imbalance Problem for LiDAR-based Object Detector by Balanced Gradients and Contextual Ground Truth Sampling. In ArXiv.

PDF Cite

Yujin Jeong, Seongbeom Park, Suhong Moon, Jinkyu Kim (2022). Zero-shot Visual Commonsense Immorality Prediction. In BMVC 2022.

Cite Code

Wonseok Roh, Gyusam Chang, Seokha Moon, Giljoo Nam, Chanyoung Kim, Younghyun Kim, Sangpil Kim, Jinkyu Kim (2022). ORA3D Overlap Region Aware Multi-view 3D Object Detection. In BMVC 2022.

PDF Cite

Seung Hyun Lee, Gyeongrok Oh, Wonmin Byeon, Jihyun Bae, Chanyoung Kim, Won Jeong Ryoo, Sang Ho Yoon, Jinkyu Kim, Sangpil Kim (2022). Sound-guided Semantic Video Generation. In ECCV 2022.

PDF Cite Code Project

Sunwoo Kim, Nokyung Park, Siwon Kim, Seunghyun Park, Jinkyu Kim (2022). Grounding Visual Representations with Texts for Domain Generalization. In ECCV 2022.

PDF Cite Code Dataset

Hyejin Lee, Daehee Kim, Daeun Lee, Jinkyu Kim, Jaekoo Lee (2022). Bridging the Domain Gap towards Generalization in Automatic Colorization. In ECCV 2022.

PDF Cite Code

Yujin Jeong, Seongbeom Park, Suhong Moon, Jinkyu Kim (2022). Zero-shot Visual Commonsense Immorality Prediction (Abstracted Version). In CVPRW 2022.

Cite

Seung Hyun Lee, Wonseok Roh, Wonmin Byeon, Sang Ho Yoon, Chanyoung Kim, Jinkyu Kim, Sangpil Kim (2022). Sound-Guided Semantic Image Manipulation. In CVPR 2022.

PDF Cite Code Project

Jinkyu Kim, Reza Mahjourian, Scott Ettinger, Mayank Bansal, Brandyn White, Benjamin Sapp, Dragomir Anguelov (2022). StopNet: Scalable Trajectory and Occupancy Prediction for Urban Autonomous Driving. In ICRA.

PDF Cite

Reza Mahjourian, Jinkyu Kim, Yuning Chai, Mingxing Tan, Benjamin Sapp, Dragomir Anguelov (2022). Occupancy Flow Fields for Motion Forecasting in Autonomous Driving. In RA-L/ICRA.

PDF Cite

Jinkyu Kim, Anna Rohrbach, Zeynep Akata, Suhong Moon, Teruhisa Misu, Yi-Ting Chen, Trevor Darrell, John Canny (2021). Towards Explainable and Advisable Model for Self-driving Cars. In Applied AI Letters.

PDF Cite

Seung Hyun Lee, Sang Ho Yoon, Jinkyu Kim, Sangpil Kim (2021). Sound-guided Semantic Image Manipulation. In NeurIPS Workshop.

PDF Cite

Seung Hyun Lee, Nahyuk Lee, Chanyoung Kim, Wonjeong Ryoo, Jinkyu Kim, Sang Ho Yoon, Sangpil Kim (2021). Audio-Semantic Image Synthesis for Artistic Paintings. In NeurIPS Workshop.

PDF Cite

Francis Indaheng, Edward Kim, Kesav Viswanadha, Jay Shenoy, Jinkyu Kim, Daniel J. Fremont, Sanjit A. Seshia (2021). A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation. In NeurIPS Workshop 2021.

PDF Cite Code

Daehee Kim, Jinkyu Kim, Jaekoo Lee (2021). Inter-domain curriculum learning for domain generalization. In ICT Express.

PDF Cite Code

Daehee Kim, Seunghyun Park, Jinkyu Kim, Jaekoo Lee (2021). SelfReg: Self-supervised Contrastive Regularization for Domain Generalization. In ICCV.

PDF Cite Code

Suhong Moon, Domas Buracas, Jinkyu Kim, John Canny (2021). BMWReg: Brownian-diffusive, Multiview, Whitening Regulararizations for Self-supervised Learning. In ICMLW.

Cite Poster

Jinkyu Kim, Mayank Bansal (2021). Towards an Interpretable Deep Driving Network by Attentional Bottleneck. In RA-L.

PDF Cite Video