Cross-modal Full-mode Fine-grained Alignment For Text-to-image Person Retrieval

Abstract

Text-to-Image Person Retrieval (TIPR) is a cross-modal matching task designed to identify the person images that best correspond to a given textual description. The key difficulty in TIPR is to realize robust correspondence between the textual and visual modalities within a unified latent representation space. To address this challenge, prior approaches incorporate attention mechanisms for implicit cross-modal local alignment. However, they lack the ability to verify whether all local features are correctly aligned. Moreover, existing methods tend to emphasize the utilization of hard negative samples during model optimization to strengthen discrimination between positive and negative pairs, often neglecting incorrectly matched positive pairs. To mitigate these problems, we propose FMFA, a cross-modal Full-Mode Fine-grained Alignment framework, which enhances global matching through explicit fine-grained alignment and existing implicit relational reasoning -- hence the term ``full-mode'

Stats

• citations0
• S2 citations—
• github stars12
• HF likes0
• heat score2.23
• arxiv keyyin2025cross

Related papers

• Text-guided Image Restoration And Semantic Enhancement For Text-to-image Person Retrieval (2023)9.00
• Multilingual Text-to-image Person Retrieval Via Bidirectional Relation Reasoning And Aligning (2025)2.35
• Beat: Bi-directional One-to-many Embedding Alignment For Text-based Person Retrieval (2024)10.85
• Cross-modal Implicit Relation Reasoning And Aligning For Text-to-image Person Retrieval (2023)18.15
• Multi-path Exploration And Feedback Adjustment For Text-to-image Person Retrieval (2024)0.00
• See Finer, See More: Implicit Modality Alignment For Text-based Person Retrieval (2022)18.39
• A New Fine-grained Alignment Method For Image-text Matching (2023)0.00
• TIPCB: A Simple But Effective Part-based Convolutional Baseline For Text-based Person Search (2021)20.24