超越全局相似性：面向细粒度、多条件多模态检索
Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval
AI总结：
MCMR提出一个多条件多模态检索基准，通过细粒度多模态检索评估模型在复杂查询中的条件感知推理能力。
摘要：
近年来，多模态大语言模型（MLLMs）的进步显著扩展了多模态检索的能力，使系统能够对视觉和文本模态进行对齐和检索。然而，现有基准主要关注粗粒度或单一条件对齐，忽视了现实场景中用户查询指定多个相互依赖约束的跨模态情况。为弥合这一差距，我们引入MCMR（多条件多模态检索）：一个大规模基准，用于评估细粒度、多条件跨模态检索在自然语言查询下的能力。MCMR涵盖五个产品领域：上装和下装、珠宝、鞋类和家具。它还保留了丰富的长文本元数据，对于组合匹配至关重要。每个查询整合互补的视觉和文本属性，要求模型共同满足所有指定条件以确保相关性。我们对多样化的MLLM多模态检索器和视觉语言重排序器进行基准测试，以评估其条件感知推理能力。实验结果揭示：（i）模型在不同模态上存在显著的不对称性；（ii）视觉线索主导早期排序精度，而文本元数据稳定了长尾排序；（iii）基于MLLM的点排序器通过显式验证查询-候选一致性显著提高了细粒度匹配。总体而言，MCMR建立了一个具有挑战性和诊断性的基准，推动多模态检索向组合、约束感知和可解释的理解发展。我们的代码和数据集可在https://github.com/EIT-NLP/MCMR上获取。
英文摘要：
Recent advances in multimodal large language models (MLLMs) have substantially expanded the capabilities of multimodal retrieval, enabling systems to align and retrieve information across visual and textual modalities. Yet, existing benchmarks largely focus on coarse-grained or single-condition alignment, overlooking real-world scenarios where user queries specify multiple interdependent constraints across modalities. To bridge this gap, we introduce MCMR (Multi-Conditional Multimodal Retrieval): a large-scale benchmark designed to evaluate fine-grained, multi-condition cross-modal retrieval under natural-language queries. MCMR spans five product domains: upper and bottom clothing, jewelry, shoes, and furniture. It also preserves rich long-form metadata essential for compositional matching. Each query integrates complementary visual and textual attributes, requiring models to jointly satisfy all specified conditions for relevance. We benchmark a diverse suite of MLLM-based multimodal retrievers and vision-language rerankers to assess their condition-aware reasoning abilities. Experimental results reveal: (i) distinct modality asymmetries across models; (ii) visual cues dominate early-rank precision, while textual metadata stabilizes long-tail ordering; and (iii) MLLM-based pointwise rerankers markedly improve fine-grained matching by explicitly verifying query-candidate consistency. Overall, MCMR establishes a challenging and diagnostic benchmark for advancing multimodal retrieval toward compositional, constraint-aware, and interpretable understanding. Our code and dataset is available at https://github.com/EIT-NLP/MCMR
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
