Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of self-supervision …
Here, we provide the proofs for Propositions 2 and 3; additional details on the proposed new instances of DeepMVC; the datasets used for evaluation; the hyperparameters used by …
J Xu, Y Ren, H Tang, Z Yang, L Pan… - … on Knowledge and …, 2022 - ieeexplore.ieee.org
Multi-view clustering is an important research topic due to its capability to utilize complementary information from multiple views. However, there are few methods to consider …
J Xu, Y Ren, X Wang, L Feng… - Proceedings of the …, 2024 - openaccess.thecvf.com
Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners. Multiple views provide more information than single views and …
Deep multi-view clustering has been widely studied. However, since it is an unsupervised task, where no labels are used to guide the training, it is still unreliable especially when …
Z Shu, B Li, C Mao, S Gao, Z Yu - Neurocomputing, 2024 - Elsevier
Multi-view clustering (MVC) technology performs unsupervised clustering on data collected from multiple sources, and has received intense attention in recent years. However, most …
J Chen, H Mao, WL Woo… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature …
R Chen, Y Tang, W Zhang, W Feng - Neural Networks, 2024 - Elsevier
Multi-view clustering has attracted growing attention owing to its powerful capacity of multi- source information integration. Although numerous advanced methods have been proposed …
R Li, C Zhang, H Fu, X Peng… - Proceedings of the …, 2019 - openaccess.thecvf.com
Multi-view clustering is a long-standing important research topic, however, remains challenging when handling high-dimensional data and simultaneously exploring the …