SOURCE-LINKED INTELLIGENCE

HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Although recent Multimodal Large Language Models (MLLMs) have advanced general product understanding, they implicitly encode product information into global embeddings, thereby limiting their ability to capture fine-grained attributes. This limitation hinders performance in tasks requiring precise attribute discrimination, such as distinguishing subtle material differences among visually similar products. To address this challenge, we propose HMGCLIP, a unified multimodal embedding framework. By constructing a heterogeneous hypergraph, we leverage hypergraph topology to mine structure-aware ha

Read original source ↗ Open in workspace

recordType

paper

region

Global