Text based Person Retrieval
24 papers with code • 3 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Text based Person Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
CUHK-PEDES
RSTPReid
ICFG-PEDES
Most implemented papers
Text-Based Person Search with Limited Data
Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch.
Learning Semantic-Aligned Feature Representation for Text-based Person Search
reallsp/SAF
•
•
In this paper, we propose a semantic-aligned embedding method for text-based person search, in which the feature alignment across modalities is achieved by automatically learning the semantic-aligned visual features and textual features.
See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval
tencentyouturesearch/personretrieval-ivt
•
•
To explore the fine-grained alignment, we further propose two implicit semantic alignment paradigms: multi-level alignment (MLA) and bidirectional mask modeling (BMM).
CLIP-Driven Fine-grained Text-Image Person Re-identification
Secondly, cross-grained feature refinement (CFR) and fine-grained correspondence discovery (FCD) modules are proposed to establish the cross-grained and fine-grained interactions between modalities, which can filter out non-modality-shared image patches/words and mine cross-modal correspondences from coarse to fine.
A Simple and Robust Correlation Filtering Method for Text-based Person Search
Suo-Wei/SRCF
•
•
ECCV 2022 2022
Text-based person search aims to associate pedestrian images with natural language descriptions.
Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision.
PLIP: Language-Image Pre-training for Person Representation Learning
zplusdragon/plip
•
•
Extensive experiments demonstrate that our model not only significantly improves existing methods on all these tasks, but also shows great ability in the few-shot and domain generalization settings.
RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
RA offsets the overfitting risk by introducing a novel positive relation detection task (i. e., learning to distinguish strong and weak positive pairs).
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
Shuyu-XJTU/APTM
•
•
To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text.
An Empirical Study of CLIP for Text-based Person Search
TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS.
