Presents a new retrieval system that enriches user queries with an intent taxonomy to improve matching of natural language descriptions to infographic designs and support authoring.
M ega P airs: Massive Data Synthesis for Universal Multimodal Retrieval
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AFMRL uses MLLM-generated attributes in attribute-guided contrastive learning and retrieval-aware reinforcement to achieve SOTA fine-grained multimodal retrieval on e-commerce datasets.
citing papers explorer
-
Show Me the Infographic I Imagine: Intent-Aware Infographic Retrieval for Authoring Support
Presents a new retrieval system that enriches user queries with an intent taxonomy to improve matching of natural language descriptions to infographic designs and support authoring.
-
AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce
AFMRL uses MLLM-generated attributes in attribute-guided contrastive learning and retrieval-aware reinforcement to achieve SOTA fine-grained multimodal retrieval on e-commerce datasets.