Metraipolis › archive › dc_28fa6f1a5628

Generative Retrieval for Unsupervised Text-Based Person Search — arXiv:2609.12965

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12965
License (as archived): CC0-1.0
Archived: 2026-10-16T03:03:42.299Z
SHA-256 of the archived text: f1dac54e25eabe0e8e4a4259dfd08b289660e1d0c564c6ef36e4cebac4c3d0de
Stable URL of this page: https://metraipolis.com/documento/dc_28fa6f1a5628

How to cite

Generative Retrieval for Unsupervised Text-Based Person Search — arXiv:2609.12965 — arXiv (en), https://arxiv.org/abs/2609.12965 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28fa6f1a5628 (Metraipolis archive dc_28fa6f1a5628, sha256 f1dac54e25eabe0e8e4a4259dfd08b289660e1d0c564c6ef36e4cebac4c3d0de)

BibTeX

@misc{dc28fa6f1a5628,
  title = {Generative Retrieval for Unsupervised Text-Based Person Search — arXiv:2609.12965},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12965},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28fa6f1a5628; sha256 f1dac54e25eabe0e8e4a4259dfd08b289660e1d0c564c6ef36e4cebac4c3d0de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12965. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-based person search (TBPS) aims to retrieve images of a target person from a large image gallery based on a given natural language description. Most existing methods rely on supervised learning with manually annotated image-text pairs. In this paper, we explore unsupervised TBPS, with only unlabeled images. We propose GTR+, a two-stage generation-then-retrieval framework. In the generation stage, we introduce a tiered description generation framework designed to produce fine-grained and stylistically diverse textual descriptions through a three-tier sequential process. The base tier leverages an automated question-and-answer mechanism to generate basic visual attribute descriptions; the intermediate tier enhances fine-grained detail using an inter-sample contrastive mechanism; the advanced tier further enriches textual diversity via a stylized expansion mechanism. In the retrieval stage, to mitigate the impact of noisy pseudo texts, we develop an adaptive confidence-weighted retrieval learning framework. We model image-text pairs as clean or noisy using a Gaussian Mixture Model, calibrated by real-time image-text similarity and static text generation probability from the prior stage, yielding adaptive sample weights during training. Beyond that, we also contribute LargeFine-Person, a large-scale TBPS dataset with high-quality, fine-grained, and diverse textual annotations, enabling a practical and generalizable TBPS pre-training benchmark under unsupervised setting. Experiments on multiple TBPS benchmarks demonstrate the effectiveness and generalization of both GTR+ and LargeFine-Person. Code is available at: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12965 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.957Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).