Text based Person Retrieval

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 30 papers with code (49 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification
  9 Dec 2023 2 repositories listed
  Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras.
• Learning Granularity-Unified Representations for Text-to-Image Person Re-identification
  16 Jul 2022 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  In PGU, we adopt a set of shared and learnable prototypes as the queries to extract diverse and semantically aligned features for both modalities in the granularity-unified feature space, which further promotes the ReID…
• Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
  8 Jan 2021 2 repositories listed
  Secondly, a BERT with locality-constrained attention is proposed to obtain representations of descriptions at different scales.
• ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language
  15 May 2020 2 repositories listed
  Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions.
• Dual-Path Convolutional Image-Text Embeddings with Instance Loss
  15 Nov 2017 2 repositories listed
  In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space.
• CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval
  26 Apr 2025 1 repository listed
  Due to the high cost of annotation and privacy protection, researchers resort to synthesized data for the paradigm of pretraining and fine-tuning.
• UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval
  14 Apr 2025 1 repository listed
  Text-based Person Retrieval (TPR) as a multi-modal task, which aims to retrieve the target person from a pool of candidate images given a text description, has recently garnered considerable attention due to the…
• An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval
  28 Mar 2025 1 repository listed
  (1) We propose an inter-class image generation pipeline, in which an automatic prompt construction strategy is introduced to guide generative Artificial Intelligence (AI) models in generating various inter-class images…
• MARS: Paying more attention to visual attributes for text-based person search
  5 Jul 2024 1 repository listed
  The task is that of retrieving one or more images of a specific individual based on a textual description.
• From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search
  16 Apr 2024 1 repository listed
  In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation.
• UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity
  6 Dec 2023 1 repository listed
  Firstly, we construct a new \textbf{dataset} named UFine6926.
• Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
  25 Nov 2023 1 repository listed
  To address the above limitations, we propose a new Composed Person Retrieval (CPR) task, which combines visual and textual queries to identify individuals of interest from large-scale person image databases.
• CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval
  18 Sep 2023 1 repository listed
  Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query.
• An Empirical Study of CLIP for Text-based Person Search
  19 Aug 2023 1 repository listed
  TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS.
• Noisy-Correspondence Learning for Text-to-Image Person Re-identification
  19 Aug 2023 1 repository listed Syntology ran 12 of 14 samples · 2 unverified · 14 pointer-only (licence)
  Text-to-image person re-identification (TIReID) is a compelling topic in the cross-modal community, which aims to retrieve the target person based on a textual query.
• Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
  5 Jun 2023 1 repository listed Syntology ran 6 of 12 samples · 6 unverified
  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.
• RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
  23 May 2023 1 repository listed Syntology ran 3 of 7 samples · 4 unverified
  RA offsets the overfitting risk by introducing a novel positive relation detection task (i.
• PLIP: Language-Image Pre-training for Person Representation Learning
  15 May 2023 1 repository listed Syntology ran 0 of 9 samples · 9 unverified
  To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP.
• Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
  22 Mar 2023 1 repository listed Syntology ran 5 of 9 samples · 4 unverified
  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…
• A Simple and Robust Correlation Filtering Method for Text-based Person Search
  4 Nov 2022 1 repository listed
  Text-based person search aims to associate pedestrian images with natural language descriptions.
• CLIP-Driven Fine-grained Text-Image Person Re-identification
  19 Oct 2022 1 repository listed Syntology ran 10 of 12 samples · 2 unverified
  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…
• See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval
  18 Aug 2022 1 repository listed
  To explore the fine-grained alignment, we further propose two implicit semantic alignment paradigms: multi-level alignment (MLA) and bidirectional mask modeling (BMM).
• Learning Semantic-Aligned Feature Representation for Text-based Person Search
  13 Dec 2021 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  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…
• Text-Based Person Search with Limited Data
  20 Oct 2021 1 repository listed
  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…
• Text-based Person Search in Full Images via Semantic-Driven Proposal Generation
  27 Sep 2021 1 repository listed
  Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance.
• DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
  12 Sep 2021 1 repository listed
  Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality.
• Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification
  27 Jul 2021 1 repository listed
  Third, we introduce a Compound Ranking (CR) loss that makes use of textual descriptions for other images of the same identity to provide extra supervision, thereby effectively reducing the intra-class variance in…
• TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search
  25 May 2021 1 repository listed
  Text-based person search is a sub-task in the field of image retrieval, which aims to retrieve target person images according to a given textual description.
• Deep Cross-Modal Projection Learning for Image-Text Matching
  1 Sep 2018 1 repository listed
  The key point of image-text matching is how to accurately measure the similarity between visual and textual inputs.
• Person Search with Natural Language Description
  19 Feb 2017 1 repository listed
  Searching persons in large-scale image databases with the query of natural language description has important applications in video surveillance.

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.