Evdclip: Improving Vision-language Retrieval With Entity Visual Descriptions From Large Language Models

Abstract

Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to generate Entity Visual Descriptions (EVDs) as alignment cues to complement textual data. These EVDs are then integrated into raw queries to create visually-rich, EVD-enhanced queries. Furthermore, recognizing that EVD-enhanced queries may introduce noise or low-quality expansions, we develop a novel, trainable EVD-aware Rewriter (EaRW) for vision-language retrieval tasks. EaRW utilizes EVD knowledg

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymeng2025evdclip

Related papers

• Evo-retriever: Llm-guided Curriculum Evolution With Viewpoint-pathway Collaboration For Multimodal Document Retrieval (2026)0.00
• Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models And Vision Language Models (2024)8.82
• ELIP: Enhanced Visual-language Foundation Models For Image Retrieval (2025)2.26
• Learning The Visualness Of Text Using Large Vision-language Models (2023)4.52
• VL-CLIP: Enhancing Multimodal Recommendations Via Visual Grounding And Llm-augmented CLIP Embeddings (2025)2.26
• Leveraging Retrieval-augmented Tags For Large Vision-language Understanding In Complex Scenes (2024)0.00
• Leveraging Large Vision-language Model As User Intent-aware Encoder For Composed Image Retrieval (2024)3.58
• A Little More Like This: Text-to-image Retrieval With Vision-language Models Using Relevance Feedback (2025)0.00