Donghyun Kim

papers

1,413

total citations

papers (25)

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

CVPR 2023arXiv

472

citations

Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density

ICCV 2021arXiv

citations

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

ICCV 2023arXiv

citations

A Unified Framework for Domain Adaptive Pose Estimation

ECCV 2022arXiv

citations

Learning to Scale Multilingual Representations for Vision-Language Tasks

ECCV 2020arXiv

citations

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

CVPR 2024arXiv

citations

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

CVPR 2023arXiv

citations

Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval

CVPR 2024arXiv

citations

What How and When Should Object Detectors Update in Continually Changing Test Domains?

CVPR 2024arXiv

citations

Adaptive Self-training Framework for Fine-grained Scene Graph Generation

ICLR 2024arXiv

citations

Learning Human Action Recognition Representations Without Real Humans

NEURIPS 2023arXiv

citations

RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning

AAAI 2025arXiv

citations

PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling

AAAI 2025arXiv

citations

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

CVPR 2025arXiv

citations

CDS: Cross-Domain Self-Supervised Pre-Training

ICCV 2021

citations

OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization

NEURIPS 2021

citations

MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval

ICCV 2025

citations

CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation

ICCV 2023

citations

Towards Efficient Image Compression Without Autoregressive Models

NEURIPS 2023

citations

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models

ICCV 2025arXiv

citations

CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning

ICCV 2025arXiv

citations

Donghyun Kim

papers (25)

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

Universal Domain Adaptation through Self Supervision

A Broad Study of Pre-training for Domain Generalization and Adaptation

Learning Cross-Modal Contrastive Features for Video Domain Adaptation

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

A Unified Framework for Domain Adaptive Pose Estimation

Learning to Scale Multilingual Representations for Vision-Language Tasks

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval

What How and When Should Object Detectors Update in Continually Changing Test Domains?

Adaptive Self-training Framework for Fine-grained Scene Graph Generation

Learning Human Action Recognition Representations Without Real Humans

RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning

PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

CDS: Cross-Domain Self-Supervised Pre-Training

OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization

MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval

CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation

Towards Efficient Image Compression Without Autoregressive Models

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models

CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning

papers (25)

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

Universal Domain Adaptation through Self Supervision

A Broad Study of Pre-training for Domain Generalization and Adaptation

Learning Cross-Modal Contrastive Features for Video Domain Adaptation

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

A Unified Framework for Domain Adaptive Pose Estimation

Learning to Scale Multilingual Representations for Vision-Language Tasks

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval

What How and When Should Object Detectors Update in Continually Changing Test Domains?

Adaptive Self-training Framework for Fine-grained Scene Graph Generation

Learning Human Action Recognition Representations Without Real Humans

RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning

PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

CDS: Cross-Domain Self-Supervised Pre-Training

OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization

MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval

CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation

Towards Efficient Image Compression Without Autoregressive Models

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models

CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning