Junsik Kim

73 papers A* 12A 7Misc 1Journal 43Unranked 10
YearRankTypeTitle / Venue / Authors
2026 J jnl
Normality-calibrated autoencoder for unsupervised anomaly detection on data contamination.
Neurocomputing
Jongmin Yu, Minkyung Kim, Junsik Kim, Hyeontaek Oh
2026 A* conf
Virtual Multiplex Staining for Histological Images Using a Marker-Wise Conditioned Diffusion Model.
AAAI
Hyun-Jic Oh, Junsik Kim, Zhiyi Shi, Yichen Wu, Yu-An Chen, Peter K. Sorger, Hanspeter Pfister, Won-Ki Jeong
2025 J jnl
DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models.
CoRR
Zhiyi Shi, Binjie Wang, Chongjie Si, Yichen Wu, Junsik Kim, Hanspeter Pfister
2025 J jnl
Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models.
Trans. Mach. Learn. Res.
Salma Abdel Magid, Weiwei Pan, Simon Warchol, Grace Guo, Junsik Kim, Mahia Rahman, Hanspeter Pfister
2025 J jnl
Spatial-Temporal Pre-Training for Embryo Viability Prediction Using Time-Lapse Videos.
CoRR
Zhiyi Shi, Junsik Kim, Helen Y. Yang, Yonghyun Song, Hyun-Jic Oh, Dalit Ben-Yosef, Daniel Needleman, Hanspeter Pfister
2025 J jnl
Toward Interactive Sound Source Localization: Better Align Sight and Sound!
IEEE Trans. Pattern Anal. Mach. Intell.
Arda Senocak, Hyeonggon Ryu, Junsik Kim, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung
2025 J jnl
Virtual Multiplex Staining for Histological Images using a Marker-wise Conditioned Diffusion Model.
CoRR
Hyun-Jic Oh, Junsik Kim, Zhiyi Shi, Yichen Wu, Yu-An Chen, Peter K. Sorger, Hanspeter Pfister, Won-Ki Jeong
2024 — conf
$\mathrm R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding.
ECCV (41)
Ye Liu, Jixuan He, Wanhua Li, Junsik Kim, Donglai Wei, Hanspeter Pfister, Chang Wen Chen
2024 J jnl
Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion.
CoRR
Jixuan He, Wanhua Li, Ye Liu, Junsik Kim, Donglai Wei, Hanspeter Pfister
2024 J jnl
Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment.
CoRR
Arda Senocak, Hyeonggon Ryu, Junsik Kim, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung
2024 J jnl
An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination.
IEEE Trans. Neural Networks Learn. Syst.
Minkyung Kim, Jongmin Yu, Junsik Kim, Tae-Hyun Oh, Jun Kyun Choi
2024 A conf
Blurry Video Compression A Trade-off between Visual Enhancement and Data Compression.
WACV
Dawit Mureja Argaw, Junsik Kim, In So Kweon
2024 J jnl
ENInst: Enhancing weakly-supervised low-shot instance segmentation.
Pattern Recognit.
Moon Ye-Bin, Dongmin Choi, Yongjin Kwon, Junsik Kim, Tae-Hyun Oh
2024 J jnl
Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models.
CoRR
Salma Abdel Magid, Weiwei Pan, Simon Warchol, Grace Guo, Junsik Kim, Mahia Rahman, Hanspeter Pfister
2024 A* conf
Joint-Task Regularization for Partially Labeled Multi-Task Learning.
CVPR
Kento Nishi, Junsik Kim, Wanhua Li, Hanspeter Pfister
2024 J jnl
Joint-Task Regularization for Partially Labeled Multi-Task Learning.
CoRR
Kento Nishi, Junsik Kim, Wanhua Li, Hanspeter Pfister
2024 J jnl
MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing Modality.
CoRR
Zhiyi Shi, Junsik Kim, Wanhua Li, Yicong Li, Hanspeter Pfister
2024 — conf
MoRA: LoRA Guided Multi-modal Disease Diagnosis with Missing Modality.
MICCAI (3)
Zhiyi Shi, Junsik Kim, Wanhua Li, Yicong Li, Hanspeter Pfister
2024 — conf
Multimodal Learning for Embryo Viability Prediction in Clinical IVF.
MICCAI (5)
Junsik Kim, Zhiyi Shi, Davin Jeong, Johannes Knittel, Helen Y. Yang, Yonghyun Song, Wanhua Li, Yicong Li, Dalit Ben-Yosef, Daniel Needleman, Hanspeter Pfister
2024 J jnl
Multimodal Learning for Embryo Viability Prediction in Clinical IVF.
CoRR
Junsik Kim, Zhiyi Shi, Davin Jeong, Johannes Knittel, Helen Y. Yang, Yonghyun Song, Wanhua Li, Yicong Li, Dalit Ben-Yosef, Daniel Needleman, Hanspeter Pfister
2024 J jnl
R
CoRR
Ye Liu, Jixuan He, Wanhua Li, Junsik Kim, Donglai Wei, Hanspeter Pfister, Chang Wen Chen
2024 J jnl
Weakly Supervised Contrastive Learning for Unsupervised Vehicle Reidentification.
IEEE Trans. Neural Networks Learn. Syst.
Jongmin Yu, Hyeontaek Oh, Minkyung Kim, Junsik Kim
2023 J jnl
Active anomaly detection based on deep one-class classification.
CoRR
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
2023 J jnl
Active anomaly detection based on deep one-class classification.
Pattern Recognit. Lett.
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
2023 J jnl
An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination.
CoRR
Minkyung Kim, Jongmin Yu, Junsik Kim, Tae-Hyun Oh, Jun Kyun Choi
2023 J jnl
Blurry Video Compression: A Trade-off between Visual Enhancement and Data Compression.
CoRR
Dawit Mureja Argaw, Junsik Kim, In So Kweon
2023 J jnl
ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation.
CoRR
Moon Ye-Bin, Dongmin Choi, Yongjin Kwon, Junsik Kim, Tae-Hyun Oh
2023 A conf
Event-Specific Audio-Visual Fusion Layers: A Simple and New Perspective on Video Understanding.
WACV
Arda Senocak, Junsik Kim, Tae-Hyun Oh, Dingzeyu Li, In So Kweon
2023 A* conf
Sound Source Localization is All about Cross-Modal Alignment.
ICCV
Arda Senocak, Hyeonggon Ryu, Junsik Kim, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung
2023 J jnl
Sound Source Localization is All about Cross-Modal Alignment.
CoRR
Arda Senocak, Hyeonggon Ryu, Junsik Kim, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung
2023 J jnl
Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics.
CoRR
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
2022 J jnl
Audio-Visual Fusion Layers for Event Type Aware Video Recognition.
CoRR
Arda Senocak, Junsik Kim, Tae-Hyun Oh, Hyeonggon Ryu, Dingzeyu Li, In So Kweon
2022 A* conf
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification.
ICRA
Jongmin Yu, Junsik Kim, Minkyung Kim, Hyeontaek Oh
2022 J jnl
Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with Point Supervision via Active Selection.
CoRR
Fei Pan, François Rameau, Junsik Kim, In So Kweon
2022 J jnl
Learning Sound Localization Better From Semantically Similar Samples.
CoRR
Arda Senocak, Hyeonggon Ryu, Junsik Kim, In So Kweon
2022 Misc conf
Learning Sound Localization Better from Semantically Similar Samples.
ICASSP
Arda Senocak, Hyeonggon Ryu, Junsik Kim, In So Kweon
2022 A conf
Less Can Be More: Sound Source Localization With a Classification Model.
WACV
Arda Senocak, Hyeonggon Ryu, Junsik Kim, In So Kweon
2022 — conf
ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation.
ECCV (34)
Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim, In So Kweon
2022 J jnl
ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation.
CoRR
Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim, In So Kweon
2022 — conf
Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics.
ICDM (Workshops)
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
2021 J jnl
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification.
CoRR
Jongmin Yu, Junsik Kim, Minkyung Kim, Hyeontaek Oh
2021 J jnl
Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications.
IEEE Trans. Pattern Anal. Mach. Intell.
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
2021 A* conf
Motion-blurred Video Interpolation and Extrapolation.
AAAI
Dawit Mureja Argaw, Junsik Kim, François Rameau, In So Kweon
2021 J jnl
Motion-blurred Video Interpolation and Extrapolation.
CoRR
Dawit Mureja Argaw, Junsik Kim, François Rameau, In So Kweon
2021 J jnl
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination.
CoRR
Jongmin Yu, Hyeontaek Oh, Minkyung Kim, Junsik Kim
2021 A* conf
Optical Flow Estimation from a Single Motion-blurred Image.
AAAI
Dawit Mureja Argaw, Junsik Kim, François Rameau, Jae-Won Cho, In So Kweon
2021 J jnl
Optical Flow Estimation from a Single Motion-blurred Image.
CoRR
Dawit Mureja Argaw, Junsik Kim, François Rameau, Jae-Won Cho, In So Kweon
2021 A conf
ResNet or DenseNet? Introducing Dense Shortcuts to ResNet.
WACV
Chaoning Zhang, Philipp Benz, Dawit Mureja Argaw, Seokju Lee, Junsik Kim, François Rameau, Jean-Charles Bazin, In So Kweon
2021 — conf
Restoration of Video Frames From a Single Blurred Image With Motion Understanding.
CVPR Workshops
Dawit Mureja Argaw, Junsik Kim, François Rameau, Chaoning Zhang, In So Kweon
2021 J jnl
Restoration of Video Frames from a Single Blurred Image with Motion Understanding.
CoRR
Dawit Mureja Argaw, Junsik Kim, François Rameau, Chaoning Zhang, In So Kweon
2020 A conf
DeepPTZ: Deep Self-Calibration for PTZ Cameras.
WACV
Chaoning Zhang, François Rameau, Junsik Kim, Dawit Mureja Argaw, Jean-Charles Bazin, In So Kweon
2020 J jnl
ResNet or DenseNet? Introducing Dense Shortcuts to ResNet.
CoRR
Chaoning Zhang, Philipp Benz, Dawit Mureja Argaw, Seokju Lee, Junsik Kim, François Rameau, Jean-Charles Bazin, In So Kweon
2019 J jnl
Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications.
CoRR
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
2019 A conf
Revisiting Residual Networks with Nonlinear Shortcuts.
BMVC
Chaoning Zhang, François Rameau, Seokju Lee, Junsik Kim, Philipp Benz, Dawit Mureja Argaw, Jean-Charles Bazin, In So Kweon
2019 J jnl
Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time.
IEEE Trans. Pattern Anal. Mach. Intell.
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon
2019 A* conf
Variational Prototyping-Encoder: One-Shot Learning With Prototypical Images.
CVPR
Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
2019 J jnl
Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images.
CoRR
Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
2019 A conf
Visuomotor Understanding for Representation Learning of Driving Scenes.
BMVC
Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon
2019 J jnl
Visuomotor Understanding for Representation Learning of Driving Scenes.
CoRR
Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon
2018 A* conf
Co-Domain Embedding Using Deep Quadruplet Networks for Unseen Traffic Sign Recognition.
AAAI
Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
2018 A* conf
Learning to Localize Sound Source in Visual Scenes.
CVPR
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
2018 J jnl
Learning to Localize Sound Source in Visual Scenes.
CoRR
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
2018 — conf
On Learning Association of Sound Source and Visual Scenes.
CVPR Workshops
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
2018 — conf
Part-Based Player Identification Using Deep Convolutional Representation and Multi-Scale Pooling.
CVPR Workshops
Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon
2017 J jnl
Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition.
CoRR
Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
2017 A* conf
Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks.
ICCV
Jae Shin Yoon, François Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
2017 J jnl
Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks.
CoRR
Jae Shin Yoon, François Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
2017 A* conf
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition.
ICCV
Seokju Lee, Junsik Kim, Jae Shin Yoon, Seunghak Shin, Oleksandr Bailo, Namil Kim, Tae-Hee Lee, Hyun Seok Hong, Seung-Hoon Han, In So Kweon
2017 J jnl
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition.
CoRR
Seokju Lee, Junsik Kim, Jae Shin Yoon, Seunghak Shin, Oleksandr Bailo, Namil Kim, Tae-Hee Lee, Hyun Seok Hong, Seung-Hoon Han, In So Kweon
2016 A* conf
Globally Optimal Manhattan Frame Estimation in Real-Time.
CVPR
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In-So Kweon
2016 — conf
Human body part classification from optical flow.
URAI
Junsik Kim, Kyungdon Joo, Tae Hyun Oh, In-So Kweon
2016 J jnl
Real-time Robust Manhattan Frame Estimation: Global Optimality and Applications.
CoRR
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In-So Kweon
2014 — conf
A fusion approach for robust visual object tracking in crowd scenes.
URAI
Tae Hyun Oh, Kyungdon Joo, Junsik Kim, Jaesik Park, In-So Kweon