| MARS: Paying more attention to visual attributes for text-based person search | ✓ Link | 77.62 | 90.63 | 94.27 | 71.41 | | | | MARS | 2024-07-05 |
| Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark | ✓ Link | 76.53 | 90.04 | 94.15 | 66.91 | | | | APTM | 2023-06-05 |
| RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search | ✓ Link | 76.51 | 90.29 | 94.25 | 69.38 | | | | RaSa | 2023-05-23 |
| From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search | ✓ Link | 76.38 | 89.72 | 93.49 | 67.22 | | | | WoRA | 2024-04-16 |
| A Simple and Robust Correlation Filtering Method for Text-based Person Search | ✓ Link | 64.88 | 83.02 | 88.56 | | | | | SRCF | 2022-11-04 |
| []() | | 64.21 | | | | | | | LGUR | |
| Learning Semantic-Aligned Feature Representation for Text-based Person Search | ✓ Link | 64.13 | 82.62 | 88.4 | | | | | SAF | 2021-12-13 |
| Text-Based Person Search with Limited Data | ✓ Link | 64.08 | 81.73 | 88.19 | 60.08 | | | | TextReID | 2021-10-20 |
| TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search | ✓ Link | 63.63 | 82.82 | 89.01 | | | | | TIPCB | 2021-05-25 |
| AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification | | 61.9 | 79.4 | 85.75 | 57.38 | | | | AXM-Net | 2021-01-19 |
| Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification | ✓ Link | 61.37 | 80.15 | 86.73 | | | | | SSAN | 2021-07-27 |
| DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval | ✓ Link | 59.98 | 80.41 | 87.56 | | | | | DSSL | 2021-09-12 |
| Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search | ✓ Link | 59.94 | 79.86 | 86.7 | | | | | NAFS | 2021-01-08 |
| Hierarchical Gumbel Attention Network for Text-based Person Search | | 59.00 | 79.49 | 86.62 | | | | | HGAN | 2020-10-10 |
| Text-based Person Search via Attribute-aided Matching | | 56.68 | 77.18 | 84.86 | | | | | CMAAM | 2020-03-14 |
| ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language | ✓ Link | 55.97 | 75.84 | 83.52 | | | | | ViTAA | 2020-05-15 |
| Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments | | 53.10 | 75.00 | 82.90 | | | | | MIA | 2019-06-23 |
| Deep Cross-Modal Projection Learning for Image-Text Matching | ✓ Link | 49.37 | - | 79.27 | | | | | CMPM+CMPC | 2018-09-01 |
| Dual-Path Convolutional Image-Text Embeddings with Instance Loss | ✓ Link | 44.4 | 66.26 | 75.07 | | | | | Dual Path | 2017-11-15 |
| Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association | | 43.58 | 66.93 | 76.26 | | | | | GLA | 2018-08-05 |
| Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval | | | | | 68.87 | 78.37 | 94.58 | 91.57 | CADA | 2023-12-04 |