arXiv:2509.16674v3 Announce Type: replace 
Abstract: Text-based Pedestrian Retrieval (TPR) deals with retrieving specific target pedestrians in visual scenes according to natural language descriptions. Although existing methods have achieved progress under constrained settings, interactive retrieval in the open-world scenario still suffers from limited model generalization and insufficient semantic understanding. To address these challenges, we propose FitPro, an open-world interactive zero-shot TPR framework with enhanced semantic comprehension and cross-scene adaptability. FitPro has three innovative components: Feature Contrastive Decoding (FCD), Incremental Semantic Mining (ISM), and Query-aware Hierarchical Retrieval (QHR). The FCD integrates prompt-guided contrastive decoding to generate high-quality structured pedestrian descriptions from denoised images, effectively alleviating semantic drift in zero-shot scenarios. The ISM constructs holistic pedestrian representations from multi-view observations to achieve global semantic modeling in multi-turn interactions, thereby improving robustness against viewpoint shifts and fine-grained variations in descriptions. The QHR dynamically optimizes the retrieval pipeline according to query types, enabling efficient adaptation to multi-modal and multi-view inputs. Extensive experiments on five public datasets and two evaluation protocols demonstrate that FitPro significantly overcomes the generalization limitations and semantic modeling constraints of existing methods in interactive retrieval, paving the way for practical deployment.

تم تقديم FitPro كإطار عمل بدون طلقات مصمم لاسترجاع المشاة التفاعلي القائم على النص في البيئات المفتوحة. تتناول هذه الطريقة المبتكرة قيود الأساليب الحالية، التي تكافح مع تعميم النموذج والفهم الدلالي في المشاهد المرئية الديناميكية.

FitPro se ha presentado como un marco de cero disparos diseñado para la recuperación interactiva de peatones basada en texto en entornos abiertos. Este enfoque innovador aborda las limitaciones de los métodos existentes, que luchan con la generalización del modelo y la comprensión semántica en escenas visuales dinámicas.

FitPro a été présenté comme un cadre zéro-shot conçu pour la récupération interactive de piétons basée sur du texte dans des environnements ouverts. Cette approche innovante répond aux limitations des méthodes existantes, qui peinent avec la généralisation des modèles et la compréhension sémantique dans des scènes visuelles dynamiques.

FitPro has been introduced as a zero-shot framework designed for interactive text-based pedestrian retrieval in open-world environments. This innovative approach addresses the limitations of existing methods, which struggle with model generalization and semantic understanding in dynamic visual scenes.

FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World

One More Thing in AI – Your Shortcut to AI Mastery

FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World

Was this article worth reading? Share it

One More Thing in AI

Humanize AI

Airparser

GPTHumanizer

AI Humanizer

Sellm

Ready to build your own newsroom?