{"ID":2896528,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06744","arxiv_id":"2507.06744","title":"Dual-Granularity Cross-Modal Identity Association for Weakly-Supervised Text-to-Person Image Matching","abstract":"Weakly supervised text-to-person image matching, as a crucial approach to reducing models' reliance on large-scale manually labeled samples, holds significant research value. However, existing methods struggle to predict complex one-to-many identity relationships, severely limiting performance improvements. To address this challenge, we propose a local-and-global dual-granularity identity association mechanism. Specifically, at the local level, we explicitly establish cross-modal identity relationships within a batch, reinforcing identity constraints across different modalities and enabling the model to better capture subtle differences and correlations. At the global level, we construct a dynamic cross-modal identity association network with the visual modality as the anchor and introduce a confidence-based dynamic adjustment mechanism, effectively enhancing the model's ability to identify weakly associated samples while improving overall sensitivity. Additionally, we propose an information-asymmetric sample pair construction method combined with consistency learning to tackle hard sample mining and enhance model robustness. Experimental results demonstrate that the proposed method substantially boosts cross-modal matching accuracy, providing an efficient and practical solution for text-to-person image matching.","short_abstract":"Weakly supervised text-to-person image matching, as a crucial approach to reducing models' reliance on large-scale manually labeled samples, holds significant research value. However, existing methods struggle to predict complex one-to-many identity relationships, severely limiting performance improvements. To address...","url_abs":"https://arxiv.org/abs/2507.06744","url_pdf":"https://arxiv.org/pdf/2507.06744v1","authors":"[\"Yafei Zhang\",\"Yongle Shang\",\"Huafeng Li\"]","published":"2025-07-09T10:59:13Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\",\"cs.MM\"]","methods":"[]","has_code":false}