{
  "abstract": "RGB-Thermal (RGB-T) salient object detection localizes salient regions where appearance cues alone are insufficient, since thermal radiation stays informative under poor illumination. Two limitations persist. Cross-modal attention is applied at a strength fixed in advance, so a momentarily uninformative stream continues to contribute in full, and directional reasoning is confined to the two image axes, because diagonal coverage has required a dense affinity mask of quadratic cost. We present CDRNet, a Confidence and Directional Reasoning Network with dual ResNet-50 encoders. Cross-modal attention is reliability-gated: a coefficient estimated for each modality from spatial entropy and gradient energy scales the transferred context through a gated residual, and the attention scale is derived from the cosine discrepancy between the pooled modality embeddings, so sharpness follows the semantic gap instead of a fixed constant, and balanced inputs recover symmetric fusion. Directional reasoning is shear-reparameterized: a circular shear maps each diagonal onto an axis, so a single axial operator covers four orientations at axial rather than quadratic cost, a per-pixel gate exposes the learned anisotropy, and a weight-shared second stage refines the result without additional parameters. A boundary gated decoder returns edge evidence to the representation through multiplicative modulation under auxiliary supervision, and its cross scale aggregator mixes two dilation rates per branch under context-dependent weights. On VT821, VT1000, and VT5000, CDRNet attains S-measure values of 0.908, 0.949, and 0.918, surpasses 19 recent methods on all metrics, and ablations isolate each contribution.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Kamal M. Othman"
    },
    {
      "name": "Abdulfattah Noorwali"
    },
    {
      "name": "Manal Abdullah Alohali"
    },
    {
      "name": "Inam Ullah"
    },
    {
      "name": "Mi Young Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6wh4w2jzkaefa.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-72418-w",
  "fulltext_url": null,
  "id": "6wh4w2jzkaefa",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://www.nature.com/articles/s41598-026-72418-w",
  "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|Visual Attention and Saliency Detection"
    ]
  ],
  "openalex": "W7215069337",
  "pdf_url": "https://www.nature.com/articles/s41598-026-72418-w_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/6wh4w2jzkaefa.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.1038/s41598-026-72418-w",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41598-026-72418-w"
    }
  ],
  "subjects": [],
  "title": "Reliability gated cross-modal attention with shear reparameterized directional reasoning for RGB-thermal salient object detection",
  "title_text": "Reliability gated cross-modal attention with shear reparameterized directional reasoning for RGB-thermal salient object detection",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/6wh4w2jzkaefa",
  "venue": "Scientific Reports",
  "versions": []
}