Publications

"ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion"

Sungho Koh, SeungJu Cha, Hyunwoo Oh, Kwanyoung Lee, Dong-Jin Kim

Neural Information Processing Systems (NeurIPS), 2025. (24.52% accept rate)

[PDF]

"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning"

MinJu Jeon, Si-Woo Kim, Ye-Chan Kim, HyunGee Kim, Dong-Jin Kim

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025.  (long, main) (22.16% accept rate)

[PDF]

"FlawMatch: Conditional Defect Image Generation via Flow Matching for Improved Surface Defect Classification"

Hyunwoo Oh, Seunghee Choi, Jinho Baek, {Dong-Jin Kim*, Junegak Joung*} (* Co-corresponding authors)

Advanced Engineering Informatics (AEI), 2025. (Impact Factor 9.9)

[PDF]

"SIDA: Synthetic Image Driven Zero-shot Domain Adaptation"

Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim

ACM International Conference on Multimedia (MM), 2025. (??% accept rate)

[PDF]

• Also presented at "Workshop on Curated Data for Efficient Learning" in conjunction with ICCV 2025.

"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning"

Si-Woo Kim, MinJu Jeon, Ye-Chan Kim, Soeun Lee, Taewhan Kim, Dong-Jin Kim

ACM International Conference on Multimedia (MM), 2025. (??% accept rate)

[PDF]

• Also presented at "Workshop on Curated Data for Efficient Learning" in conjunction with ICCV 2025.

"CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation"

Hyunwoo Oh, SeungJu Cha, Kwanyoung Lee, Si-Woo Kim, Dong-Jin Kim

ACM International Conference on Multimedia (MM), 2025. (??% accept rate)

[PDF]

"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness"

SeungJu Cha, Kwanyoung Lee, Ye-Chan Kim, Hyunwoo Oh, Dong-Jin Kim

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (22.1% accept rate)

[PDF] [code]

• Also presented at "Workshop on AI for Creative Visual Content Generation Editing and Understanding" in conjunction with CVPR 2025.

"ViPCap: Retrieval Text-based Visual Prompts for Lightweight Image Captioning"

Taewhan Kim, Soeun Lee, Si-Woo Kim, Dong-Jin Kim

AAAI Conference on Artificial Intelligence (AAAI), 2025.  (23.4% accept rate)

[PDF]

• Also presented at "Workshop on Adaptive Foundation Models" in conjunction with NeurIPS 2024.

"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning"

{Soeun Lee*, Si-Woo Kim*}, Taewhan Kim, Dong-Jin Kim (* Co-first authors)

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.  (long, main) (20.8% accept rate)

[PDF] [code]

• Also presented at "Workshop on Adaptive Foundation Models" and "Workshop on Video-Language Models" in conjunction with NeurIPS 2024.

"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality"

Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon, Junmo Kim

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. (long, main)  (20.8% accept rate)

[PDF]

"Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data"

Dong-Jin Kim, Tae-Hyun Oh,  Jinsoo Choi, and In So Kweon.

IEEE Access, 2024. (Impact Factor 3.4)

[PDF]

"Empirical study on using Adapters for debiased Visual Question Answering"

Jae Won Cho, Dawit Mureja Argaw, Yeongtaek Oh, Dong-Jin Kim, In So Kweon

Computer Vision and Image Understanding (CVIU), 2023. (Impact Factor 4.5)

[PDF]

"Counterfactual Mix-Up for Visual Question Answering"

{Jae Won Cho*, Dong-Jin Kim*}, Yunjae Jung, In So Kweon  (* Co-first authors)

IEEE Access, 2023. (Impact Factor 3.9)

[PDF]

"Technical Report of NICE Challenge at CVPR 2023: Retrieval-based Data Discovery and Fusion for Zero-shot Image Captioning"

Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon, Jumno Kim

preprint, 2023.

[PDF] [code]

• 2nd place in the NICE Challenge at CVPR 2023

"Local Pseudo-Attributes for Long-Tailed Recognition"

Dong-Jin Kim, Tsung-Wei Ke, Stella X. Yu

Pattern Recognition Letters (PRL), 2023. (Impact Factor 5.1)

[PDF]

• Also presented at the "Self-Supervised Learning: Theory and Practice" workshop in conjunction with NeurIPS 2022.

"Modeling Semantic Correlation and Hierarchy for Real-world Wildlife Recognition"

Dong-Jin Kim, Zhongqi Miao, Yunhui Guo, Stella X. Yu

IEEE Signal Processing Letters (SPL), 2023. (Impact Factor 3.201)

[PDF]

• Also presented at "Workshop on Human in the Loop Learning"  in conjunction with NeurIPS 2022.

"Generative Bias for Robust Visual Question Answering"

Jae Won Cho, Dong-Jin Kim, Hyeonggon Ryu, and In So Kweon,

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2023. (25.78% accept rate)

[PDF] [code]

• • Received Bronze Prize, 28th Samsung Humantech Paper Awards (Top 2.8%)

  • Received Excellent Paper Award, IW-FCV 2023

  • Also presented at "Workshop on Open-Domain Reasoning Under Multi-Modal Settings"  in conjunction with CVPR 2023

"Self-Sufficient Framework for Continuous Sign Language Recognition"

YeongJun Jang, Youngtaek Oh, Jae Won Cho, Myungchul Kim, Dong-Jin Kim, In  So  Kweon,  and Joon Son Chung

International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. 

[PDF] [Project]

"Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition"

YeongJun Jang, Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, Joon Son Chung,  and In  So  Kweon

British Machine Vision Conference (BMVC), 2022. 

[PDF] [Project] [code]

"DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning"

YoungTaek Oh, Dong-Jin Kim, and In So Kweon.

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (25.3% accept rate)

[PDF] [Project]  [code]

• Also presented at "Workshop on Learning with Limited Labelled Data for Image and Video Understanding"  in conjunction with CVPR 2022.

"MCDAL: Maximum Classifier Discrepancy for Active Learning"

{Jae  Won  Cho*, Dong-Jin  Kim*},  Yunjae  Jung, and In So Kweon (* Co-first authors)

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. (Impact Factor 14.255)  

[PDF][arXiv] [code]

• Also presented at "The Workshop on Fine-Grained Visual Categorization"  in conjunction with CVPR 2022.

"Dense Relational Image Captioning via Multi-task Triple-Stream Networks"

Dong-Jin Kim, Tae-Hyun Oh,  Jinsoo Choi, and In So Kweon.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (Impact Factor 24.314)  

[PDF][arXiv] [Project] [Dataset] [code]

• Received Qualcomm Innovation Award 2019.

"Single-Modal Entropy based Active Learning for Visual Question Answering"

{Dong-Jin  Kim*, Jae  Won  Cho*},  Jinsoo Choi, Yunjae  Jung,  and In  So  Kweon (* Co-first authors)

British Machine Vision Conference (BMVC), 2021. 

[PDF]

"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection"

Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, and In So Kweon,

IEEE Transactions on Image Processing (TIP),  2021. (Impact Factor 10.856)

[PDF][arXiv] [Project] [code] 

"LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation"

Inkyu Shin, Dong-Jin  Kim,  Jae  Won  Cho, Sanghyun Woo, KwanYong Park, and In So Kweon

IEEE International Conference on Computer Vision (ICCV),  2021.  (Oral) (3% accept rate)

[PDF]

• Winner of Qualcomm Innovation Fellowship 2021.

"Dealing  with  Missing  Modalities  in  the  Visual  Question  Answer-Difference  Prediction Task through Knowledge Distillation"

Jae  Won  Cho, Dong-Jin  Kim,  Yunjae  Jung,  Jinsoo  Choi, and In So Kweon

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Multimodal Learning and Applications Workshop,  2021.  

[PDF]

• Also presented at "Visual Question Answering Workshop" and "VizWiz Grand Challenge Workshop" in conjunction with CVPR 2021.

"Detecting Human-Object Interactions with Action Co-occurrence Priors"

Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, and In So Kweon,

European Conference on Computer Vision (ECCV), 2020.  (27% accept rate)

[PDF] [Project] [code] [Slides] [Video] [Poster]

• Received Silver Prize, 26th Samsung Humantech Paper Awards (Top 1.6%)

• Also presented at "The 2nd workshop on Video Turing Test: Toward Human-Level Video Story Understanding" in conjunction with ECCV 2020.

"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach"

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh,  and In So Kweon.

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019.  (23.8% accept rate)

[PDF] [Project] [Slides] [Poster]

• Also, presented at "Language&Vision " and  "Visual Question Answering and Dialog " Workshops in conjunction with CVPR 2019, and "CLVL: 3rd Workshop on Closing the Loop Between Vision and Language" in conjunction with ICCV 2019.

"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning"

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh,  and In So Kweon.

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019.  (25.2% accept rate)

[PDF] [Project] [Dataset] [code] [Slides] [Poster]

• Extension of this work received Qualcomm Innovation Award 2019.

• Also presented at "Language&Vision"  and "Visual Question Answering and Dialog" Workshops in conjunction with CVPR 2019.

"Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks"

Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, Youngjin Yoon, and In So Kweon.

IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. (Oral)

[PDF]