Gunhee Kim

Affiliations

rippleAISeoul National University

papers

498

total citations

papers (28)

Imbalanced Continual Learning with Partitioning Reservoir Sampling

ECCV 2020arXiv

126

citations

Rethinking Class Activation Mapping for Weakly Supervised Object Localization

ECCV 2020

120

citations

ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning

ICCV 2021arXiv

citations

Continual Learning on Noisy Data Streams via Self-Purified Replay

ICCV 2021arXiv

citations

Panoramic Vision Transformer for Saliency Detection in 360° Videos

ECCV 2022arXiv

citations

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

NEURIPS 2021arXiv

citations

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

ICCV 2023arXiv

citations

Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

ICLR 2025arXiv

citations

Spherical World-Locking for Audio-Visual Localization in Egocentric Videos

ECCV 2024arXiv

citations

ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images

CVPR 2024arXiv

citations

HalLoc: Token-level Localization of Hallucinations for Vision Language Models

CVPR 2025arXiv

citations

ChartCap: Mitigating Hallucination of Dense Chart Captioning

ICCV 2025arXiv

citations

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams

CVPR 2025arXiv

citations

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

ICLR 2024arXiv

citations

Transitional Adaptation of Pretrained Models for Visual Storytelling

CVPR 2021

citations

StyleMix: Separating Content and Style for Enhanced Data Augmentation

CVPR 2021

citations

Constrained GPI for Zero-Shot Transfer in Reinforcement Learning

NEURIPS 2022

citations

Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos

ICCV 2021

citations

Viewpoint-Agnostic Change Captioning With Cycle Consistency

ICCV 2021

citations

Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation

ICCV 2023arXiv

citations

Character Grounding and Re-Identification in Story of Videos and Text Descriptions

ECCV 2020

citations

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

NEURIPS 2023

citations

FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields

ICCV 2025arXiv

citations

Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning

ECCV 2020

citations

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning

CVPR 2023

citations

Gunhee Kim

Affiliations

papers (28)

Imbalanced Continual Learning with Partitioning Reservoir Sampling

Rethinking Class Activation Mapping for Weakly Supervised Object Localization

ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning

Continual Learning on Noisy Data Streams via Self-Purified Replay

Panoramic Vision Transformer for Saliency Detection in 360° Videos

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

Recasting Continual Learning as Sequence Modeling

Federated Learning via Meta-Variational Dropout

Learning to Continually Learn with the Bayesian Principle

Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

Spherical World-Locking for Audio-Visual Localization in Egocentric Videos

ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images

HalLoc: Token-level Localization of Hallucinations for Vision Language Models

ChartCap: Mitigating Hallucination of Dense Chart Captioning

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

Transitional Adaptation of Pretrained Models for Visual Storytelling

StyleMix: Separating Content and Style for Enhanced Data Augmentation

Constrained GPI for Zero-Shot Transfer in Reinforcement Learning

Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos

Viewpoint-Agnostic Change Captioning With Cycle Consistency

Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation

Character Grounding and Re-Identification in Story of Videos and Text Descriptions

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields

Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning

papers (28)

Imbalanced Continual Learning with Partitioning Reservoir Sampling

Rethinking Class Activation Mapping for Weakly Supervised Object Localization

ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning

Continual Learning on Noisy Data Streams via Self-Purified Replay

Panoramic Vision Transformer for Saliency Detection in 360° Videos

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

Recasting Continual Learning as Sequence Modeling

Federated Learning via Meta-Variational Dropout

Learning to Continually Learn with the Bayesian Principle

Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

Spherical World-Locking for Audio-Visual Localization in Egocentric Videos

ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images

HalLoc: Token-level Localization of Hallucinations for Vision Language Models

ChartCap: Mitigating Hallucination of Dense Chart Captioning

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

Transitional Adaptation of Pretrained Models for Visual Storytelling

StyleMix: Separating Content and Style for Enhanced Data Augmentation

Constrained GPI for Zero-Shot Transfer in Reinforcement Learning

Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos

Viewpoint-Agnostic Change Captioning With Cycle Consistency

Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation

Character Grounding and Re-Identification in Story of Videos and Text Descriptions

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields

Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning