EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Query-Driven Candidate Relation Screening for Scene Graph-Based Visual Relation Retrieval

Wan Wang, Ke Wang, Huiqin Wang

Applied Sciences · 15.05.2026 · 16 (10) · 4947

DOI: 10.3390/app16104947 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.05.2026. Verfasst von Wan Wang und 2 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Program Funded by Education Department of Shaanxi Provincial Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scene graph generation (SGG) provides a structured representation for visual understanding. However, most existing methods are designed to optimize global triplet recall rather than retrieve relation instances specified by a user query. In query-driven visual relation retrieval, two major challenges arise: the target relation must compete with a highly redundant candidate space, and query semantics are not incorporated before relation classification. To address these challenges, we propose a Query-Driven Candidate Relation Screening (QCRS) module, which injects query semantics into the candidate screening process. Specifically, QCRS encodes the query and candidate visual relation features, and then filters query-relevant candidates through relevance scoring. By reducing interference from irrelevant candidates and avoiding redundant computation, QCRS improves the final exact triplet hit performance and enhances the interpretability of query-specific relations, thereby facilitating query-driven visual relation retrieval. Built upon the strong EGTR baseline, QCRS learns query relevance to prioritize relation instances matching the target query, enabling precise triplet retrieval. Extensive ablation studies and analyses on the VG150 benchmark validate the effectiveness of the proposed approach: when integrated with EGTR, QCRS improves PairR@50 from 61.52% to 80.06% and ETR@50 from 30.54% to 47.07%, achieving absolute gains of over 16 percentage points in both correct object pair retention and end-to-end target relation retrieval performance.

Förderung

  • Scientific Research Program Funded by Education Department of Shaanxi Provincial Government

Zitieren

APA

Wang, W., Wang, K., & Wang, H. (2026). Query-Driven Candidate Relation Screening for Scene Graph-Based Visual Relation Retrieval. Applied Sciences, 16(10), 4947. https://doi.org/10.3390/app16104947

Vancouver

Wang W, Wang K, Wang H. Query-Driven Candidate Relation Screening for Scene Graph-Based Visual Relation Retrieval. Applied Sciences. 2026;16(10):4947. doi:10.3390/app16104947

BibTeX
@article{Wang2026,
  author = {Wang, Wan and Wang, Ke and Wang, Huiqin},
  title = {Query-Driven Candidate Relation Screening for Scene Graph-Based Visual Relation Retrieval},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {4947},
  doi = {10.3390/app16104947}
}
Kostenlos starten →