Seungju Han

Affiliations

Stanford

papers

438

total citations

papers (13)

Disentangling Label Distribution for Long-Tailed Visual Recognition

CVPR 2021arXiv

293

citations

Towards Accurate Facial Landmark Detection via Cascaded Transformers

CVPR 2022arXiv

citations

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

ICLR 2025arXiv

citations

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

ICCV 2023arXiv

citations

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

NEURIPS 2025arXiv

citations

CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision

ICCV 2023

citations

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

CVPR 2023

citations

Sample-wise Label Confidence Incorporation for Learning with Noisy Labels

ICCV 2023

citations

Seungju Han

Affiliations

papers (13)

Disentangling Label Distribution for Long-Tailed Visual Recognition

Towards Accurate Facial Landmark Detection via Cascaded Transformers

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Pushing the Performance Limit of Scene Text Recognizer Without Human Annotation

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

Quality-Agnostic Image Recognition via Invertible Decoder

Rethinking Feature-Based Knowledge Distillation for Face Recognition

CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

Sample-wise Label Confidence Incorporation for Learning with Noisy Labels

papers (13)

Disentangling Label Distribution for Long-Tailed Visual Recognition

Towards Accurate Facial Landmark Detection via Cascaded Transformers

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Pushing the Performance Limit of Scene Text Recognizer Without Human Annotation

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

Quality-Agnostic Image Recognition via Invertible Decoder

Rethinking Feature-Based Knowledge Distillation for Face Recognition

CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

Sample-wise Label Confidence Incorporation for Learning with Noisy Labels