Proceedings

kgMBQA: Quality Knowledge Graph-driven Multimodal Blind Image Assessment

Wuyuan Xie, Tingcheng Bian, Miaohui Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 4245-4253.

https://doi.org/10.24963/ijcai.2025/473

Keywords

  • Humans and AI: HAI: Cognitive modeling
  • Humans and AI: HAI: Cognitive systems
  • Humans and AI: HAI: Personalization and user modeling
  • Humans and AI: HAI: Applications

Abstract

Blind image assessment aims to simulate human prediction of image quality distortion levels and provide quality scores. However, existing unimodal quality indicators have limited representational ability when facing complex contents and distortion types, and the predicted scores also fail to provide explanatory reasons, which further affects the credibility of their prediction results. To address these challenges, we propose a multimodal quality indicator with explanatory text descriptions, called kgMBQA. Specifically, we construct an image quality knowledge graph and conduct in-depth mining to generate explanatory texts. The text modality is further aligned and fused with the image modality, thereby improving the model performance while also outputting its corresponding quality explanatory description. The experimental results demonstrate that our kgMBQA achieves the best performance compared to recent representative methods on the KonIQ-10k, LIVE Challenge, BIQ2021, TID2013, and AIGC-3K datasets.

Wuyuan Xie, Tingcheng Bian, and Miaohui Wang. 2025. kgMBQA: Quality Knowledge Graph-driven Multimodal Blind Image Assessment. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 4245–4253. https://doi.org/10.24963/ijcai.2025/473
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards