activity
20202026
most citedKnowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

31 citations · 55 across the 16 of their papers we have counts for

collaborators
Showing cs.AIShow all

8 papers · 1 filter

cs.AI2025

Multi-modal Knowledge Graph Generation with Semantics-enriched Prompts

Yajing Xu, Zhiqiang Liu, Jiaoyan Chen +7

Multi-modal Knowledge Graphs (MMKGs) have been widely applied across various domains for knowledge representation. However, the existing MMKGs are significantly fewer than required…

cs.AI2024

Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

Yichi Zhang, Zhuo Chen, Lingbing Guo +5

Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning, which can enhance reasoning tasks withi…

cs.AI2024

Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation

Yichi Zhang, Zhuo Chen, Lingbing Guo +5

Multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given knowledge graphs, collaboratively leveraging structural information from the triples…

cs.AI202431 cited

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

Zhuo Chen, Yichi Zhang, Yin Fang +12

Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for…

cs.AI20232 cited

Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment

Zhuo Chen, Lingbing Guo, Yin Fang +6

As a crucial extension of entity alignment (EA), multi-modal entity alignment (MMEA) aims to identify identical entities across disparate knowledge graphs (KGs) by exploiting assoc…

cs.AI20215 cited

Zero-shot Visual Question Answering using Knowledge Graph

Zhuo Chen, Jiaoyan Chen, Yuxia Geng +3

Incorporating external knowledge to Visual Question Answering (VQA) has become a vital practical need. Existing methods mostly adopt pipeline approaches with different components f…