Search Results for author: Myong Chol Jung

Found 5 papers, 1 papers with code

Personalised Outfit Recommendation via History-aware Transformers

no code implementations29 Jun 2024 Myong Chol Jung, Julien Monteil, Philip Schulz, Volodymyr Vaskovych

We present the history-aware transformer (HAT), a transformer-based model that uses shoppers' purchase history to personalise outfit predictions.

Navigating Conflicting Views: Harnessing Trust for Learning

no code implementations3 Jun 2024 Jueqing Lu, Lan Du, Wray Buntine, Myong Chol Jung, Joanna Dipnall, Belinda Gabbe

Resolving conflicts is essential to make the decisions of multi-view classification more reliable.

Enhancing Near OOD Detection in Prompt Learning: Maximum Gains, Minimal Costs

no code implementations25 May 2024 Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, Lan Du

In this study, we investigate the near OOD detection capabilities of prompt learning models and observe that commonly used OOD scores have limited performance in near OOD detection.

Out of Distribution (OOD) Detection

Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking

1 code implementation12 Apr 2024 Tianyu Zhu, Myong Chol Jung, Jesse Clark

Contrastive learning has gained widespread adoption for retrieval tasks due to its minimal requirement for manual annotations.

Contrastive Learning Retrieval

Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture

no code implementations6 Oct 2022 Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, Lan Du

Uncertainty estimation is essential to make neural networks trustworthy in real-world applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.