Dong-Jin Kim

Modeling semantic correlation and hierarchy for real-world wildlife recognition

IEEE Signal Processing Letters (SPL), 2023

2023

Empirical study on using adapters for debiased Visual Question Answering

Computer Vision and Image Understanding

2023/12/1

Semi-supervised image captioning by adversarially propagating labeled data

arXiv preprint arXiv:2301.11174

2023/1/26

NICE 2023 Zero-shot Image Captioning Challenge

arXiv preprint arXiv:2309.01961

2023/9/5

Generative bias for robust visual question answering

2023

Counterfactual Mix-Up for Visual Question Answering

IEEE Access

2023/8/10

Local pseudo-attributes for long-tailed recognition

Pattern Recognition Letters

2023/8/1

Self-sufficient framework for continuous sign language recognition

2023/6/4

Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning

2022

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

arXiv preprint arXiv:2211.00448

2022/11/1

Mcdal: Maximum classifier discrepancy for active learning

IEEE transactions on neural networks and learning systems

2022/3/22

Dealing with missing modalities in the visual question answer-difference prediction task through knowledge distillation

2021

Single-Modal Entropy based Active Learning for Visual Question Answering

arXiv preprint arXiv:2110.10906

2021/10/21

Dense relational image captioning via multi-task triple-stream networks

IEEE Transactions on Pattern Analysis and Machine Intelligence

2021/10/14

Acp++: Action co-occurrence priors for human-object interaction detection

IEEE Transactions on Image Processing

2021/9/23

Labor: Labeling only if required for domain adaptive semantic segmentation

2021

Detecting Human-Object Interactions with Action Co-occurrence Priors

2020/7/17