Saved in:
Bibliographic Details
Main Authors: Liu, Jing, Wei, Donglai, Liu, Yang, Zhang, Sipeng, Yang, Tong, Zhou, Wei, Ding, Weiping, Leung, Victor C. M.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2304.02278
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914183170228224
author Liu, Jing
Wei, Donglai
Liu, Yang
Zhang, Sipeng
Yang, Tong
Zhou, Wei
Ding, Weiping
Leung, Victor C. M.
author_facet Liu, Jing
Wei, Donglai
Liu, Yang
Zhang, Sipeng
Yang, Tong
Zhou, Wei
Ding, Weiping
Leung, Victor C. M.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_02278
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SCMM: Calibrating Cross-modal Representations for Text-Based Person Search
Liu, Jing
Wei, Donglai
Liu, Yang
Zhang, Sipeng
Yang, Tong
Zhou, Wei
Ding, Weiping
Leung, Victor C. M.
Computer Vision and Pattern Recognition
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.
title SCMM: Calibrating Cross-modal Representations for Text-Based Person Search
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.02278