Publications

From core algorithms and theoretical insights to applied systems tackling perception, language, and decision making.

GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder

Findings of Empirical Methods in Natural Language Processing (EMNLP-Findings)

Seunghyuk Cho, Zhenyue Qin, Yang Liu, Youngbin Choi, Seungbeom Lee, Dongwoo Kim
Addressing Attribute Leakage in Text Embeddings for Image Editing with Diffusion Models

International Conference on Computer Vision (ICCV)

Sunung Mun*, Jinhwan Nam*, Sunghyun Cho, Jungseul Ok
Enhancing Cost Efficiency in Active Learning with Candidate Set Query

Transactions on Machine Learning Research (TMLR)

Yeho Gwon, Sehyun Hwang, Hoyoung Kim, Jungseul Ok, Suha Kwak
Active Prompt Learning with Vision-Language Model Priors

Transactions on Machine Learning Research (TMLR)

Hoyoung Kim, Seokhee Jin, Changhwan Sung, Jaechang Kim, Jungseul Ok
MemBN: Robust Test-Time Adaptation via Batch Norm with Statistics Memory

European Conference on Computer Vision (ECCV)

Juwon Kang, Nayeong Kim, Jungseul Ok, Suha Kwak
Active Label Correction for Semantic Segmentation with Foundation Models

International Conference on Machine Learning (ICML)

Hoyoung Kim, Sehyun Hwang, Suha Kwak, Jungseul Ok
Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

International Conference on Machine Learning (ICML)

Nayeong Kim, Juwon Kang, Sungsoo Ahn, Jungseul Ok, Suha Kwak
MedBN: Robust Test-Time Adaptation against Malicious Test Samples

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Hyejin Park*, Jeongyeon Hwang*, Sunung Mun, Sangdon Park, Jungseul Ok
CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Hyeongmin Lee, Kyoungkook Kang, Jungseul Ok, Sunghyun Cho
Active Learning for Semantic Segmentation with Multi-class Label Query

Advances in Neural Information Processing Systems (NeurIPS)

Sehyun Hwang, Sohyun Lee, Hoyoung Kim, Minhyeon Oh, Jungseul Ok, Suha Kwak
Adaptive Superpixel for Active Learning in Semantic Segmentation

International Conference on Computer Vision (ICCV)

Hoyoung Kim, Minhyeon Oh, Sehyun Hwang, Suha Kwak, Jungseul Ok
Robust Evaluation of Diffusion-Based Adversarial Purification

International Conference on Computer Vision (ICCV)

Minjong Lee, Dongwoo Kim
Removing Multiple Biases through the Lens of Multi-task Learning

International Conference on Machine Learning, Workshop on Spurious Correlations, Invariance and Stability

Nayeong Kim, Juwon Kang, Sungsoo Ahn, Jungseul Ok, Suha Kwak
Leveraging Proxy of Training Data for Test-Time Adaptation

International Conference on Machine Learning (ICML)

Juwon Kang, Nayeong Kim, Donghyeon Kwon, Jungseul Ok, Suha Kwak
Anonymization for Skeleton Action Recognition

AAAI Conference on Artificial Intelligence (AAAI)

Saemi Moon*, Myeonghyeon Kim*, Zhenyue Qin, Yang Liu, Dongwoo Kim
Anonymization for Skeleton Action Recognition

Advances in Neural Information Processing Systems, Workshop on Trustworthy and Socially Responsible Machine Learning (TSRML)

Saemi Moon*, Myeonghyeon Kim*, Zhenyue Qin, Yang Liu, Dongwoo Kim
Towards Sequence-Level Training for Visual Tracking

European Conference on Computer Vision (ECCV)

Minji Kim, Seungkwan Lee, Jungseul Ok, Bohyung Han, Minsu Cho
Combating Label Distribution Shift for Active Domain Adaptation

European Conference on Computer Vision (ECCV)

Sehyun Hwang, Sohyun Lee, Sungyeon Kim, Jungseul Ok, Suha Kwak
Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns

European Conference on Computer Vision, Workshop on Real-World Surveillance (RWS)

Zhenyue Qin, Pan Ji, Dongwoo Kim, Yang Liu, Saeed Anwar, Tom Gedeon
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Jaechang Kim*, Yunjoo Lee*, Seunghoon Hong, Jungseul Ok

Publications

Active Label Correction for Semantic Segmentation with Foundation Models

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

MedBN: Robust Test-Time Adaptation against Malicious Test Samples

CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment

Active Learning for Semantic Segmentation with Multi-class Label Query

Adaptive Superpixel for Active Learning in Semantic Segmentation

Removing Multiple Biases through the Lens of Multi-task Learning

Leveraging Proxy of Training Data for Test-Time Adaptation

Towards Sequence-Level Training for Visual Tracking

Combating Label Distribution Shift for Active Domain Adaptation

Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution