Skip to content
Book Open access

From Dialogue to Evidence: Retrieval-State-Conditioned Interaction for Text-Based Person Retrieval

Nov 2026 · Proceedings of the 34th ACM International Conference on Multimedia · pp. 9717-9725 · 0 citations

Abstract

Interactive text-based person retrieval aims to resolve ambiguity in an underspecified initial query through iterative clarification. However, existing methods largely rely on free-form dialogue, which makes interaction depend on unstructured language generation rather than directly selecting the most discriminative visual evidence among competing candidates. As a result, acquired evidence is only implicitly encoded in dialogue history, remaining uncertainty is not explicitly represented, and generated questions are often weakly grounded in the visual differences that determine ranking. This limitation is further amplified by the long-tailed distribution of visual attributes: frequent attributes are easy to ask about but quickly become weakly discriminative, whereas long-tail attributes are often more informative for disambiguation yet underutilized. To address this, we reformulate interactive retrieval as a retrieval-state-conditioned evidence acquisition problem. We introduce a grounded discrete concept space composed of reusable concept atoms, which provides a shared representation for the initial query, candidate-side evidence, and user feedback. At each interaction round, the system selects the next concept atom conditioned on the current candidate set using a redundancy-aware utility that jointly favors ambiguity reduction, candidate discrimination, and high-quality partitioning of the candidate pool. In our framework, natural language serves only as an interaction interface, while decision-making is performed over structured concept-level evidence. This formulation replaces unconstrained dialogue generation with structured, utility-driven clarification, enabling targeted and interpretable interaction without training additional question-generation or interaction-policy modules. Experiments on Interactive-PEDES under a unified multi-round protocol show that our method consistently outperforms language-centric baselines, delivering faster early-stage refinement and larger cumulative improvements across interaction rounds, with R@1 improving by 31.01% over five rounds.

Read PDF

Similar papers

Nov 2026

Query Suggestion for Text-to-Image Retrieval

Cross-modal Query Suggestion, the task of dynamically generating targeted query alternatives that verbalize the semantic content of visually coherent image groups within an initial retrieval result set, is investigated, and a comprehensive evaluation framework to map the structural trade-offs is established.

Giacomo Pacini, Fabio Carrara, N. Messina et al. · 0 citations
Open access Nov 2026

A Retrieval-Augmented Conversational Framework for Intelligent Personal Document Understanding

The exponential proliferation of digital content across personal repositories—encompassing academic manuscripts, annotated lecture transcripts, technical project documentation, and domain-specific study materials—has introduced substantial challenges in efficient knowledge retrieval. Conventional information retrieval...

Vaibhav Sharma · 0 citations
Open access 2026

RADAR: Retrieval-Aligned Attribution and Dual-Perspective Reasoning for Conversational Query Rewriting

RADAR is introduced, a novel feedback-driven framework that leverages the reasoning capabilities of Large Reasoning Models (LRMs) to generate and refine queries and introduces the Attribution-based Iterative Reasoning-Rewrite Refinement (AIR3) algorithm, which drives an iterative refinement process of pruning redundant...

Jia-Rui Lu, Tao Fang, Tian-Yu Zhang et al. · 0 citations
Preprint Oct 2026

Faithful Query Resolution for Conversational Search

This paper compares five query-generation configurations within a behavior-adaptive assistant using BM25 and SPLADE retrieval, and finds that the weighted configuration obtains the highest mean retrieval scores, but this retrieval advantage does not coincide with the highest conversational satisfaction scores.

S. Zerhoudi, Ivica Kostric, Jelena Mitrović · 0 citations
Preprint Nov 2026

An Effective Spoken Language Understanding Approach Leveraging Query-Adaptive Intent Detection

Large language models enable fine-tuning-free spoken language understanding (SLU) through in-context learning, but direct query-based retrieval may select semantically similar yet intent irrelevant demonstrations. This paper presents Query-Adaptive Intent Detection via Prototype Extraction (APEX), a two-stage retrieval...

Bing-Long Kuo, Yu-Hsuan Fang, Tien-Hong Lo et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.