Self-Supervised Hypergraph Learning for Enhanced Multimodal Representation

Hypergraph neural networks have gained substantial popularity in capturing complex correlations between data items in multimodal datasets. In this study, we propose a novel approach called the self-supervised hypergraph learning (SHL) framework that focuses on extracting hypergraph features to impro...

Cijeli opis

Bibliografski detalji

Glavni autori:	Hongji Shu, Chaojun Meng, Pasquale De Meo, Qing Wang, Jia Zhu
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2024-01-01
Serija:	IEEE Access
Teme:	Multimodal micro-video self-supervised learning hypergraph neural networks
Online pristup:	https://ieeexplore.ieee.org/document/10418926/
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!