← Authors

Donghyun Kim

53 papers · 2008–2026 · 13 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (13) πŸƒ Academic Marathon (17) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (10) 🀝 Dynamic Duo (10) πŸ”¬ Deep Specialist (12) ❓ The Questioner ⚑ Prolific Year (10) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (8) πŸ—ƒοΈ Keyword Collector (212) πŸ’Ž Century Club (51) πŸ“ˆ Trend Setter

Conferences

ICCV (10) AAAI (7) CVPR (7) ECCV (6) NIPS (6) EACL (3) WACV (3) ACL (2) EMNLP (2) ICLR (2) INTERSPEECH (2) NAACL (2) CORL (1)

Top co-authors

Kate Saenko (10) Stan Sclaroff (10) Kuniaki Saito (8) Rogerio Feris (6) Chanyoung Park (5) Leonid Karlinsky (5) Rameswar Panda (5) Yeonjun In (4) Kanghoon Yoon (4) Kyong-Ho Lee (4)

Research topics

Privacy (1) Optimization & Theory (1)

Keywords

domain adaptation (8) large language model (7) self-supervised learning (4) vision language model (4) transfer learning (3) continual learning (3) scene graph generation (2) semi-supervised learning (2) contrastive learning (2) representation learning (2) knowledge distillation (2) vision transformer (2) unsupervised learning (2) few-shot learning (2) multimodal learning (2) embedding learning (2) feature alignment (2) attention mechanism (2) zero-shot learning (2) model architecture (2)

Papers

Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA EACL 2026
Universal Compressed Image Restoration via Codec-Aware Conditioning with Reinforcement Learning AAAI 2026
MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval ICCV 2025
Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning WACV 2025
PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling AAAI 2025
RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning AAAI 2025
StitchLLM: Serving LLMs, One Block at a Time ACL 2025
Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation CVPR 2025
Weakly Supervised Video Scene Graph Generation via Natural Language Supervision ICLR 2025
Large Language Models as Realistic Microservice Trace Generators EMNLP 2025
ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models ICCV 2025
CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning ICCV 2025
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs ECCV 2024
Spoken-to-written text conversion with Large Language Model INTERSPEECH 2024
Efficient and Versatile Robust Fine-Tuning of Zero-shot Models ECCV 2024
Guided conditioning with predictive network on score-based diffusion model for speech enhancement INTERSPEECH 2024
LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation CVPR 2024
What How and When Should Object Detectors Update in Continually Changing Test Domains? CVPR 2024
Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval CVPR 2024
Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection ECCV 2024
MATE: Meet At The Embedding - Connecting Images with Long Texts EMNLP 2024
Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection NIPS 2024
Grafting Vision Transformers WACV 2024
Adaptive Self-training Framework for Fine-grained Scene Graph Generation ICLR 2024
Towards Efficient Image Compression Without Autoregressive Models NIPS 2023
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap ICCV 2023
CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning CVPR 2023
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning CVPR 2023
Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models NIPS 2023
CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation ICCV 2023
Going Beyond Nouns With Vision & Language Models Using Synthetic Data ICCV 2023
Learning Human Action Recognition Representations Without Real Humans NIPS 2023
Persona Expansion with Commonsense Knowledge for Diverse and Consistent Response Generation EACL 2023
Concept-based Persona Expansion for Improving Diversity of Persona-Grounded Dialogue EACL 2023
A Broad Study of Pre-training for Domain Generalization and Adaptation ECCV 2022
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents AAAI 2022
Active Learning on Pre-trained Language Model with Task-Independent Triplet Loss AAAI 2022
A Unified Framework for Domain Adaptive Pose Estimation ECCV 2022
Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances NAACL 2022
Learning Cross-Modal Contrastive Features for Video Domain Adaptation ICCV 2021
CDS: Cross-Domain Self-Supervised Pre-Training ICCV 2021
OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization NIPS 2021
Learning to Jump from Pixels CORL 2021
Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density ICCV 2021
Learning to Scale Multilingual Representations for Vision-Language Tasks ECCV 2020
Unsupervised Attributed Multiplex Network Embedding AAAI 2020
Multi-way Encoding for Robustness WACV 2020
MULE: Multimodal Universal Language Embedding AAAI 2020
Universal Domain Adaptation through Self Supervision NIPS 2020
Conversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues NAACL 2019
Semi-Supervised Domain Adaptation via Minimax Entropy ICCV 2019
Excitation Backprop for RNNs CVPR 2018
Speakers’ Intention Prediction Using Statistics of Multi-level Features in a Schedule Management Domain ACL 2008