Google Scholar [Link]

2023

• MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models

Dohwan Ko, Joonmyung Choi, Hyeong Kyu Choi, Kyoung-Woon On, Byungseok Roh, Hyunwoo J. Kim,

Computer Vision and Pattern Recognition (CVPR), 2023. (To appear).

• Self-positioning Point-based Transformer for Point Cloud Understanding

Jinyoung Park*, Sanghyeok Lee*, Sihyeon Kim, Yunyang Xiong, Hyunwoo J. Kim,

Computer Vision and Pattern Recognition (CVPR), 2023. (To appear).

• Robust Auxiliary Learning with Weighting Function for Biased Data

Dasol Hwang, Sojin Lee, Joonmyung Choi, Je-Keun Rhe, Hyunwoo J. Kim,

Information Sciences, 2023. (Accepted)

• Relation-aware Language-Graph Transformer for Question Answering, 

Jinyoung Park*, Hyeong Kyu Choi*, Juyeon Ko*, Hyeonjin Park, Ji-Hoon Kim, Jisu Jeong, Kyungmin Kim, Hyunwoo J. Kim,

AAAI Conference on Artificial Intelligence (AAAI), 2023.

2022

• SageMix: Saliency-Guided Mixup for Point Clouds, 

Sanghyeok Lee*, Minkyu Jeon*, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim, 

Advances in Neural Information Processing Systems (NeurIPS), 2022. [Poster] [Video] [Code] 

• Invertible Monotone Operators for Normalizing Flows, 

Byeongkeun Ahn, Chiyoon Kim, Youngjoon Hong, Hyunwoo J. Kim, 

Advances in Neural Information Processing Systems (NeurIPS), 2022. [Poster] [Video] [Slides]

• TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers, 

Hyeong Kyu Choi*, Joonmyung Choi*, Hyunwoo J. Kim, 

Advances in Neural Information Processing Systems (NeurIPS), 2022. [Poster] [Video] [Code] 

• k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment,

Minkyu Jeon, Hyeonjin Park, Hyunwoo J. Kim, Michael Morley, Hyunghoon Cho,

European Conference on Computer Vision (ECCV), 2022. [Supp] [Poster] [Video] [Code]

• Video-Text Representation Learning via Differentiable Weak Temporal Alignment, 

Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh, Kyoung-Woon On, Eun-Sol Kim, Hyunwoo J. Kim, 

Computer Vision and Pattern Recognition (CVPR), 2022. [Poster] [Code]

• Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection,

Jihwan Park, SeungJun Lee, Hwan Heo, Hyeong Kyu Choi, Hyunwoo J. Kim, 

Computer Vision and Pattern Recognition (CVPR), 2022. [Poster] [Code]

• Deformable Graph Convolutional Networks, 

Jinyoung Park, Sungdong Yoo, Jihwan Park, Hyunwoo J. Kim, 

AAAI Conference on Artificial Intelligence (AAAI), 2022. [Video]

• Randomly Shuffled Convolution for Self-Supervised Representation Learning,

Youngjin Oh*, Minkyu Jeon*, Dohwan Ko, Hyunwoo J. Kim,

Information Sciences, 2022. 

• Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs, 

Seongjun Yun, Minbyul Jeong , Sungdong Yoo, Seunghun Lee, Sean S. Yi , Raehyun Kim , Jaewoo Kang and Hyunwoo J. Kim,

Neural Networks (NN), 2022.

• Explainable Time-series Prediction using a Residual Network and Gradient-based methods,

Hyojung Choi, Chanhwi Jung, Taein Kang, Hyunwoo J. Kim, Il-Youp Kwak, 

IEEE ACCESS, 2022. 

• Single cell lineage reconstruction using distance-based algorithms and the R package, DCLEAR,

Wuming Gong, Hyunwoo J. Kim, Daniel J Garry, Il-Youp Kwak, 

BMC Bioinformatics, 2022.

• Deformable Graph Transformer,

Jinyoung Park, Seongjun Yun, Hyeonjin Park, Jaewoo Kang, Jisu Jeong, Kyung-Min Kim, Jung-woo Ha, Hyunwoo J. Kim, 

Arxiv, 2022. [arxiv]

2021

• Metropolis-Hastings Data Augmentation for Graph Neural Networks, 

Hyeonjin Park*, Seunghun Lee*, Sihyeon Kim, Jinyoung Park, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim, 

Advances in Neural Information Processing Systems (NeurIPS), 2021. [Video] [Code]

• Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction,
  Seongjun Yun, Seoyoon Kim, Junhyun Lee, Jaewoo Kang, Hyunwoo J. Kim,
  Advances in Neural Information Processing Systems (NeurIPS), 2021. [Video] [Code]

• Point Cloud Augmentation with Weighted Local Transformations, 

Sihyeon Kim*, Sanghyeok Lee*, Dasol Hwang,  Jaewon Lee, Seong Jae Hwang, Hyunwoo J. Kim, 

International Conference on Computer Vision (ICCV), 2021. [Video] [Code]

• HOTR: End-to-End Human-Object Interaction Detection with Transformers,
  Bumsoo Kim, Junhyun Lee, Jaewoo Kang, Eun-Sol Kim, Hyunwoo J. Kim,
  Computer Vision and Pattern Recognition (CVPR), 2021. (Oral presentation). [Video] [Code]

• Learning Augmentation for GNNs with Consistency Regularization,
  Hyeonjin Park*, Seunghun Lee*, Dasol Hwang, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, and Hyunwoo J. Kim,
  IEEE ACCESS, 2021. 

• Learning to Balance Local Losses via Meta-Learning,
  Seungdong Yoa, Minkyu Jeon, Youngjin Oh, Hyunwoo J. Kim,
  IEEE ACCESS, 2021.

• Learning Non-parametric Surrogate Losses with Correlated Gradients,
  Seungdong Yoa*, Jinyoung Park*, Hyunwoo J. Kim,
  IEEE ACCESS, 2021.

• Search-and-Attack: Temporally SparseAdversarial Perturbations on Videos,
  Hwan Heo*, Dohwan Ko*, Jaewon Lee*, Youngjoon Hong, Hyunwoo J. Kim,
  IEEE ACCESS, 2021.

• Self-Supervised Learning for Anomaly Detection with Dynamic Local Augmentation,
  Seungdong Yoa*, Seungjun Lee*, Chiyoon Kim, and Hyunwoo J. Kim,
  IEEE ACCESS, 2021.

• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning,
  Dasol Hwang*, Jinyoung Park*, Sunyoung Kwon, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim,
  Arxiv, 2021. [arxiv]

• Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs,
  Seongjun Yun, Minbyul Jeong, Sungdong Yoo, Seunghun Lee, Sean S. Yi, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim,
  Arxiv, 2021. [arxiv]

2020

• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs,
  Dasol Hwang*, Jinyoung Park*, Sunyoung Kwon, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim,
  Advances in Neural Information Processing Systems (NeurIPS), 2020. [Video] [Code]

• UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection,
  Bumsoo Kim, Taeho Choi, Jaewoo Kang, Hyunwoo J. Kim,
  European Conference on Computer Vision (ECCV), 2020. 

• Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods,
  Byungjoo Kim, Bryce Chudomelka, Jinyoung Park, Jaewoo Kang, Youngjoon Hong, Hyunwoo J. Kim,
  European Conference on Computer Vision (ECCV), 2020.  [Code]

2019

• Graph Transformer Networks,
  Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim,
  Advances in Neural Information Processing Systems (NeurIPS), 2019. [Code]

• Sampling-free Uncertainty Estimation in Gated Recurrent Units with Applications to Normative Modeling in Neuroimaging,
  Seong Jae Hwang, Ronak R. Mehta, Hyunwoo J. Kim, Sterling C. Johnson, Vikas Singh,
  Conference on Uncertainty in Artificial Intelligence (UAI), 2019.

• Mixed Effects Neural Networks (MeNets) with Applications to Gaze Estimation,
  Yunyang Xiong, Hyunwoo J. Kim, Vikas Singh,
  Computer Vision and Pattern Recognition (CVPR), 2019.

• ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification,
  Yunyang Xiong, Hyunwoo J. Kim, Varsha Hedau,
  ECV (CVPR Workshop), 2019. (oral presentation)

• On Training Deep 3D CNN Models with Dependent Samples in Neuroimaging,
  Yunyang Xiong, Hyunwoo J. Kim, Bhargav Tangirala,Vikas Singh,
  Information Processing in Medical Imaging (IPMI), 2019. (oral presentation)

• Localizing differentially evolving covariance structures via scan statistics,
  Ronak Mehta, Hyunwoo J. Kim, Shulei Wang, Sterling C. Johnson, Ming Yuan and Vikas Singh,
  Quarterly of Applied Mathematics, 2019.

2018

• Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families,
  Seong Jae Hwang, Ronak Mehta, Hyunwoo J. Kim, Vikas Singh,
  Arxiv, 2018.

• Efficient Relative Attribute Learning using Graph Neural Networks,
  Zihang Meng, Nagesh Adluru, Hyunwoo J. Kim, Glenn Fung, and Vikas Singh,
  European Conference on Computer Vision (ECCV), 2018.

• Tensorize, Factorize and Regularize: Robust Visual Relationship Learning,
  Seong Jae Hwang, Sathya N. Ravi, Zirui Tao, Hyunwoo J. Kim, Maxwell D. Collins, Vikas Singh,
  Computer Vision and Pattern Recognition (CVPR), 2018.

2017

• Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective,
  Ronak Mehta, Hyunwoo J. Kim , Shulei Wang, Sterling C. Johnson, Ming Yuan, Vikas Singh,
  Arxiv, Nov 2017.

• Statistical Learning Models for Manifold-valued Measurements with Applications to Computer Vision and Neuroimaging,
  Hyunwoo J. Kim, PhD Thesis, University of Wisconsin-Madison, 2017.

• Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification,
  Jinseok Nam, Eneldo Loza Mencía, Hyunwoo J. Kim , Johannes Fürnkranz,
  Advances in Neural Information Processing Systems (NeurIPS), Dec 2017, (Spotlight presentation).

• Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging,
  Hyunwoo J. Kim, Nagesh Adluru, Heemanshu Suri, Baba C. Vemuri, Sterling C. Johnson, Vikas Singh,
  Computer Vision and Pattern Recognition (CVPR), Jul 2017.

• Riemannian Variance Filtering: An Independent Filtering Scheme for Statistical Tests on Manifold-valued Data,
  Ligang Zheng, Hyunwoo J. Kim, Nagesh Adluru, Michael A. Newton, Vikas Singh,
  The international Workshop on DIFFerential geometry in Computer Vision and Machine Learning (DIFF-CVML) at CVPR (CVPR Workshop), Jul 2017 (Oral presentation (slide)).

• Cover Song Identification with Metric Learning Using Distance as a Feature,
  Hoon Heo, Hyunwoo J. Kim, Wan Soo Kim, Kyogu Lee,
  The International Society of Music Information Retrieval (ISMIR), 2017.

2016

• Abundant Inverse Regression using Sufficient Reduction and its Applications,
  Hyunwoo J. Kim*, Brandon M. Smith*, Nagesh Adluru, Charles R. Dyer, Sterling C. Johnson, Vikas Singh,
  European Conference on Computer Vision (ECCV), Oct 2016. Both * are joint first authors.

• Won Hwa Kim*, Hyunwoo J. Kim*, Nagesh Adluru, Vikas Singh, Latent Variable Graphical Model Selection using Harmonic Analysis: Applications to the Human Connectome Project (HCP), In Computer Vision and Pattern Recognition (CVPR), Jun, 2016. (Spotlight presentation). Both * are joint first authors.

2015

• Interpolation on the manifold of k-component Gaussian Mixture Models (GMMs),
  Hyunwoo J. Kim, Nagesh Adluru, Monami Banerjee, Baba C. Vemuri, Vikas Singh,
  In International Conference on Computer Vision (ICCV), Dec 2015.

• Manifold-valued Dirichlet Processes,
  Hyunwoo J. Kim, Jia Xu, Baba C. Vemuri, Vikas Singh,
  In International Conference on Machine Learning (ICML), Jul 2015.

• Canonical Correlation Analysis on SPD(n) Manifolds ,
  Hyunwoo J. Kim, Nagesh Adluru, Barbara B. Bendlin, Sterling C. Johnson, Baba C. Vemuri, Vikas Singh,
  Riemannian Computing and Statistical Inferences in Computer Vision (RCCV), 2015 (Book chapter).

• Predicting Unseen Labels using Label Hierarchies in Large-Scale Multi-label Learning,
  Jinseok Nam, Eneldo Loza Mencía, Hyunwoo J. Kim , and Johannes Fürnkranz,
  European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Sep 2015.

2014

• Canonical Correlation Analysis on Riemannian Manifolds and its Applications,
  Hyunwoo J. Kim, Nagesh Adluru, Barbara B. Bendlin, Sterling C. Johnson, Baba C. Vemuri, Vikas Singh,
  European Conference on Computer Vision (ECCV), Sep 2014.

• Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images,
  Hyunwoo J. Kim, Nagesh Adluru, Maxwell D. Collins, Moo K. Chung, Barbara B. Bendlin, Sterling C. Johnson, Richard J. Davidson, Vikas Singh,
  IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2014. (Oral presentation)

Before 2014

• Evolutionary hypernetworks for learning to generate music from examples,
  H.-W. Kim , B.-H. Kim, and B.-T. Zhang,
  IEEE International Conference on Fuzzy Systems (Fuzz IEEE), Aug 2009.

• Text-to-image cross-modal retrieval of magazine articles based on higher-order pattern recall by hypernetworks,
  J.-W. Ha, B.-H. Kim, H.-W. Kim, W.C. Yoon, J.-H. Eom, and B.-T. Zhang,
  International Symposium on Advanced Intelligent Systems (ISIS), Aug 2009 (Best paper award).