{
  "abstract": "Small objects in underwater and traffic-sign images often have weak boundaries and low contrast. Downsampling and multi-scale fusion can further weaken the features needed to detect them. We propose ContextFlow-YOLO, a YOLOv8n-based detector designed to preserve context during feature extraction and reuse it across scales. Its context-preserving backbone combines local features with surrounding and global information during downsampling. The global-guided scale-sequence neck distributes this context to features at different levels. A nonlinear context-attention fusion unit then refines the responses used for prediction. ContextFlow-YOLO obtains mAP@0.5 scores of 0.855, 0.838, and 0.826 on URPC2019, URPC2020, and TT100K, respectively. On TT100K, the model uses 6.11 M parameters and runs at 134 FPS. Heatmap and receptive-field visualizations show more concentrated target responses and broader feature coverage than YOLOv8n.",
  "abstract_shown": true,
  "affiliations": [
    "Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia",
    "School of Computer Science and Artificial Intelligence, Chaohu University, Hefei 238024, China"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Yuqing Jiao",
      "orcid": "0009-0001-1966-4611"
    },
    {
      "affs": [
        0
      ],
      "name": "Siok Yee Tan",
      "orcid": "0000-0003-3566-9938"
    },
    {
      "affs": [
        0
      ],
      "name": "Fadilla ’Atyka Nor Rashid",
      "orcid": "0000-0001-6670-8560"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Huifen Xing"
    },
    {
      "affs": [
        1
      ],
      "name": "Yong Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/44crnknfby171.bib",
  "cited_by": 0,
  "doi": "10.3390/math14203781",
  "fulltext_url": null,
  "id": "44crnknfby171",
  "issns": [
    "2227-7390"
  ],
  "landing_url": "https://www.mdpi.com/2227-7390/14/20/3781",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Advanced Neural Network Applications"
    ]
  ],
  "openalex": "W7222942628",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-18",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/44crnknfby171.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:29Z",
      "native_id": "10.3390/math14203781",
      "source": "crossref",
      "url": "https://www.mdpi.com/2227-7390/14/20/3781"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "issn:2227-7390",
      "subfield": "general"
    }
  ],
  "title": "ContextFlow-YOLO: Context Preservation and Cross-Scale Redistribution for Small-Object Detection in Complex Environments",
  "title_text": "ContextFlow-YOLO: Context Preservation and Cross-Scale Redistribution for Small-Object Detection in Complex Environments",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:29Z",
  "url": "https://research.draconitic.com/paper/44crnknfby171",
  "venue": "Mathematics",
  "versions": []
}