Browse Proceedings

Despite the meaningful advancements in graph-based multi-view clustering methods, several challenges persist. Firstly, these methods often suffer from high computational costs, limiting their application to large-scale datasets. Secondly, direct ...

Recently, in order to improve the naturalness and similarity of speaker features after voice conversion while retaining most of the speaker content, research on voice conversion under non-parallel text conditions has made great progress. This ...

With increasing popularity and larger real-world applicability, graph self-supervised learning (GSSL) can significantly reduce labeling costs by extracting implicit input supervision. As a promising example, graph masked auto-encoders (GMAE) can ...

Due to the varying energy capacities and power consumption rates of Sensor Nodes (SNs), their charging needs may not coincide. Traditional Wireless Power Transfer (WPT) systems cannot handle the additional charging requirements from energy-...

Due to the remarkable capabilities of generative AI technologies, pre-trained large language models (LLMs) have been widely used. However, the high computational and memory requirements limit the widespread adoption of LLMs. It is a challenging ...

The long-tailed distribution data poses significant challenges for visual classification tasks. The existing solutions can be categorized into three main categories, i.e., class re-balancing, information augmentation, and module improvement. ...

Personalized federated learning (PFL) develops a customized model for each local client to mitigate accuracy issues caused by data and system heterogeneity of different local clients. Most works on PFL adopt a centralized federation and therefore ...

Imbalanced datasets are prevalent in real life, which have a skewed data distribution. In the research of imbalanced datasets, the inherent patterns of minority class affect the generalization performance of Machine Learning models. The re-...

The current field of 3D generation has made significant progress, yet achieving high-fidelity 3D object reconstruction from a single-view image remains a challenging task. However, we find that recent StyleGAN-based 3D GANs are primarily used for ...

Our model-free approach utilizes Vicinal Risk Minimization (VRM) to address label noise in crowd-sourced datasets, avoiding complex adjustments based on Annotator-Specific Parameters (ASPs) that struggle with sparse data and identifiability ...

Federated learning enables multiple clients to collaboratively train a shared model without transmitting their data. Although this novel approach offers significant advantages in data privacy protection, the variations in data distribution among ...

Currently, in the field of computer vision and 3D reconstruction, the pursuit of perfor mance improvement and efficiency optimization has been a common focus of researchers and engineers. To cope with the growing application demands, especially in ...

With the arrival of modern technology, research on safety inspection techniques in complex environments is crucial. Using hardware devices such as mobile devices and vision sensors combined with many algorithmic techniques can effectively improve ...

This work presents a multilabel feature selection approach via label enhancement and weighted neighborhood mutual information. First, the Fuzzy C-Means (FCM) clustering is optimized by the Whale Optimization Algorithm (WOA) to obtain the initial ...

In the field of computer vision, many perception methods rely on depth information captured by depth cameras. However, the integrity of depth maps is hindered by the reflection and refraction of light on transparent objects. Existing methods of ...