Hyunwoo J. Kim

papers

1,046

total citations

papers (22)

HOTR: End-to-End Human-Object Interaction Detection With Transformers

CVPR 2021arXiv

316

citations

UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection

ECCV 2020arXiv

180

citations

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

CVPR 2022arXiv

citations

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

CVPR 2022arXiv

citations

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

CVPR 2025arXiv

citations

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

CVPR 2024arXiv

citations

Retrieval-Augmented Open-Vocabulary Object Detection

CVPR 2024arXiv

citations

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

CVPR 2024arXiv

citations

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

ECCV 2024arXiv

citations

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

AAAI 2025arXiv

citations

K-SALSA: K-Anonymous Synthetic Averaging of Retinal Images via Local Style Alignment

ECCV 2022arXiv

citations

Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods

ECCV 2020arXiv

citations

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models

ICCV 2023arXiv

citations

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

ICCV 2023arXiv

citations

Super-Class Guided Transformer for Zero-Shot Attribute Classification

AAAI 2025arXiv

citations

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

NEURIPS 2025arXiv

citations

Hyunwoo J. Kim

papers (22)

HOTR: End-to-End Human-Object Interaction Detection With Transformers

UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection

Self-Positioning Point-Based Transformer for Point Cloud Understanding

Read-only Prompt Optimization for Vision-Language Few-shot Learning

Point Cloud Augmentation With Weighted Local Transformations

vid-TLDR: Training Free Token Merging for Light-weight Video Transformer

Prompt Learning via Meta-Regularization

MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models

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

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

Retrieval-Augmented Open-Vocabulary Object Detection

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

K-SALSA: K-Anonymous Synthetic Averaging of Retinal Images via Local Style Alignment

Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

Super-Class Guided Transformer for Zero-Shot Attribute Classification

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

papers (22)

HOTR: End-to-End Human-Object Interaction Detection With Transformers

UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection

Self-Positioning Point-Based Transformer for Point Cloud Understanding

Read-only Prompt Optimization for Vision-Language Few-shot Learning

Point Cloud Augmentation With Weighted Local Transformations

vid-TLDR: Training Free Token Merging for Light-weight Video Transformer

Prompt Learning via Meta-Regularization

MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models

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

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

Retrieval-Augmented Open-Vocabulary Object Detection

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

K-SALSA: K-Anonymous Synthetic Averaging of Retinal Images via Local Style Alignment

Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

Super-Class Guided Transformer for Zero-Shot Attribute Classification

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation