Automatic Synthetic Data And Fine-grained Adaptive Feature Alignment For Composed Person Retrieval

Abstract

Person retrieval has attracted rising attention. Existing methods are mainly divided into two retrieval modes, namely image-only and text-only. However, they are unable to make full use of the available information and are difficult to meet diverse application requirements. To address the above limitations, we propose a new Composed Person Retrieval (CPR) task, which combines visual and textual queries to identify individuals of interest from large-scale person image databases. Nevertheless, the foremost difficulty of the CPR task is the lack of available annotated datasets. Therefore, we first introduce a scalable automatic data synthesis pipeline, which decomposes complex multimodal data generation into the creation of textual quadruples followed by identity-consistent image synthesis using fine-tuned generative models. Meanwhile, a multimodal filtering method is designed to ensure the resulting SynCPR dataset retains 1.15 million high-quality and fully synthetic triplets. Additional

Stats

• citations0
• S2 citations—
• github stars74
• HF likes0
• heat score3.75
• arxiv keyliu2023automatic

Related papers

• Automatic Synthesis Of High-quality Triplet Data For Composed Image Retrieval (2025)0.00
• Towards Identity-aware Cross-modal Retrieval: A Dataset And A Baseline (2024)1.56
• Decoupled Cross-modal Alignment Network For Text-rgbt Person Retrieval And A High-quality Benchmark (2025)0.00
• Cross-modal Full-mode Fine-grained Alignment For Text-to-image Person Retrieval (2025)2.23
• Beat: Bi-directional One-to-many Embedding Alignment For Text-based Person Retrieval (2024)10.85
• Multi-path Exploration And Feedback Adjustment For Text-to-image Person Retrieval (2024)0.00
• Good4cir: Generating Detailed Synthetic Captions For Composed Image Retrieval (2025)0.00
• Scale Up Composed Image Retrieval Learning Via Modification Text Generation (2025)3.58