Text Based Person Retrieval On Rstpreid 1
Metriken
R@1
R@10
R@5
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | R@1 | R@10 | R@5 | Paper Title | Repository |
|---|---|---|---|---|---|
| DSSL | 39.05 | 73.95 | 62.60 | DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval | |
| CADA | - | - | - | Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval | - |
| IRRA | 60.20 | 81.30 | 88.20 | Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval | - |
| RDE | 65.35 | 89.90 | 83.95 | Noisy-Correspondence Learning for Text-to-Image Person Re-identification | |
| Filtering-WoRA(Small) | 66.85 | 91.10 | 86.45 | From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search | - |
| MARS | 67.55 | 91.35 | 86.65 | MARS: Paying more attention to visual attributes for text-based person search | |
| APTM | 67.50 | 91.45 | 85.70 | Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark | |
| TBPS-CLIP (ViT-B/16) | 61.95 | 88.75 | 83.55 | An Empirical Study of CLIP for Text-based Person Search | |
| RaSa | 66.90 | 91.35 | 86.50 | RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search | - |
0 of 9 row(s) selected.