PulseAugur
EN
LIVE 06:45:06

New CIRCLED dataset enhances multi-turn image retrieval research

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced CIRCLED, a new multi-turn composed image retrieval dataset designed to overcome the limitations of existing datasets, which often lack dialogue consistency and are confined to specific domains like fashion. CIRCLED features 22,608 multi-turn dialogue sessions across nine subsets, with queries progressively refining towards a target image. This dataset aims to provide a high-quality benchmark for advancing research in multi-turn image retrieval. AI

IMPACT Provides a new benchmark for improving multi-turn image retrieval systems.

RANK_REASON The cluster describes the release of a new academic dataset for a specific research task.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New CIRCLED dataset enhances multi-turn image retrieval research

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Tomohisa Takeda, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Osamu Torii, Yusuke Matsui ·

    CIRCLED: A Multi-turn CIR Dataset with Consistent Dialogues across Domains

    arXiv:2605.26734v1 Announce Type: new Abstract: Existing Multi-Turn Composed Image Retrieval (MTCIR) datasets lack dialogue-history consistency and are restricted to the fashion domain. To address these limitations, we construct CIRCLED by extending FashionIQ, CIRR, and CIRCO. In…

  2. arXiv cs.CV TIER_1 English(EN) · Yusuke Matsui ·

    CIRCLED: A Multi-turn CIR Dataset with Consistent Dialogues across Domains

    Existing Multi-Turn Composed Image Retrieval (MTCIR) datasets lack dialogue-history consistency and are restricted to the fashion domain. To address these limitations, we construct CIRCLED by extending FashionIQ, CIRR, and CIRCO. In CIRCLED, the query at each turn progressively a…

RELATED ENTITIES

RELATED TOPICS