SCMM: Calibrating Cross-modal Representations for Text-Based Person Search

TL;DR

SCMM introduces a unified framework with novel calibration and masked modeling techniques to improve cross-modal representations for text-based person search, achieving state-of-the-art results.

Contribution

The paper proposes SCMM, a new method combining sew calibration and masked caption modeling to enhance fine-grained cross-modal alignment in person search.

Findings

Achieves state-of-the-art Rank1 accuracy on CUHK-PEDES (73.81%)

Demonstrates effectiveness of each component through ablation studies

Balances representation quality and computational efficiency

Abstract

Text-Based Person Search (TBPS) aims to retrieve target person images from a large-scale gallery using natural language descriptions, posing fundamental challenges in cross-modal representation learning. Existing methods often struggle to bridge the semantic gap between heterogeneous modalities while capturing fine-grained correspondences essential for discriminating visually similar individuals. To address these challenges, we propose Sew Calibration and Masked Modeling (SCMM), a unified framework that calibrates cross-modal representations through complementary learning mechanisms. Notably, SCMM introduces two novel components: a sew calibration loss that dynamically aligns image-text features using quality-guided adaptive margins based on textual information density, and a masked caption modeling loss that establishes fine-grained cross-modal correspondences through transformer-based masked prediction. Additionally, the sew calibration mechanism implements bidirectional constraints to effectively compress same-identity features in the shared embedding space, while the masked modeling component leverages a cross-modal decoder to learn word-level visual-textual relationships, enabling discrimination of subtle attribute differences. Our dual-encoder architecture achieves an effective balance between representation capability and computational efficiency by employing a training-only decoder design. Extensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReID benchmarks demonstrate that SCMM achieves state-of-the-art performance with Rank1 accuracies of 73.81%, 64.25%, and 57.35%, respectively. Comprehensive ablation studies validate the effectiveness of each proposed component.