Abstract Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformatics, and other sciences. Due to their black …
W Yang, M Liu, Z Wang, S Liu - Computational Visual Media, 2024 - Springer
Recent studies have indicated that foundation models, such as BERT and GPT, excel at adapting to various downstream tasks. This adaptability has made them a dominant force in …
Microblogging is a popular online social network (OSN), which facilitates users to obtain and share news and information. Nevertheless, it is filled with a huge number of social bots that …
Online social networks (OSNs) are a major component of societal digitalization. OSNs alter how people communicate, make decisions, and form or change their beliefs, attitudes, and …
Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and …
C Chen, Z Wang, J Wu, X Wang… - … on Visualization and …, 2021 - ieeexplore.ieee.org
Semi-supervised learning (SSL) provides a way to improve the performance of prediction models (eg, classifier) via the usage of unlabeled samples. An effective and widely used …
C Chen, J Wu, X Wang, S Xiang… - … on Visualization and …, 2021 - ieeexplore.ieee.org
As training high-performance object detectors requires expensive bounding box annotations, recent methods resort to free-available image captions. However, detectors …
W Yang, Y Guo, J Wu, Z Wang, LZ Guo… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Label quality issues, such as noisy labels and imbalanced class distributions, have negative effects on model performance. Automatic reweighting methods identify problematic samples …
In the biomedical domain, taxonomies organize the acquisition modalities of scientific images in hierarchical structures. Such taxonomies leverage large sets of correct image …