{
  "abstract": "Autism Spectrum Disorder (ASD) affects social interaction and communication, and automatically recognizing emotions from the facial expressions of children with ASD remains challenging. A key barrier to facial emotion recognition (FER) in children with ASD is the absence of ASD-specific datasets with proper emotion-level annotations. To address this, we present ASD-FER, a benchmark of 2,779 facial images of children with ASD annotated across six emotion categories by three independent annotators using majority voting. We evaluate nine models -- CNN, SVM, AlexNet, ResNet34, ResNet50, MobileNetV2, and three backbone configurations of our proposed task-specific architecture, EQFormer: ViT, Swin-T, and a compact Hybrid CNN-Transformer (HybridT) -- under stratified 10-fold cross-validation and a held-out 90/10 evaluation. ResNet50 led conventional models at 84.89% mean cross-validation accuracy; among transformer-based models, ViT led with 88.27%, followed by Swin-T at 88.02% and HybridT at 86.58%. On the held-out set, ViT achieved the highest overall accuracy (91.01%), while Swin-T obtained the best balanced accuracy (74.47%) and macro-F1 (0.7078); HybridT remained competitive at 89.57% accuracy with a fraction of the parameters. To support explainability, Grad-CAM visualizations highlighted attention on emotion-relevant facial regions -- eyes, eyebrows, and mouth -- with Swin-T the most spatially focused and the HybridT the most parameter-efficient (2.66M). Class imbalance and cross-dataset generalization remain open challenges.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Science, LSU New Orleans, New Orleans, Louisiana, USA"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "S. Y. Chowdhury"
    },
    {
      "name": "B. Banik"
    },
    {
      "name": "T. A. Knaus"
    },
    {
      "name": "C. D. Moore"
    },
    {
      "name": "H. F. Ansah"
    },
    {
      "name": "H. Hammad"
    },
    {
      "name": "P. Ghimire"
    },
    {
      "name": "M. T. Hoque"
    },
    {
      "name": "S. Banerjee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/356wf2ar2j1y3.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.14.754143",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.full",
  "id": "356wf2ar2j1y3",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "neuroscience"
    ],
    [
      "openalex",
      "3205|Emotion and Mood Recognition"
    ]
  ],
  "openalex": "W7223023813",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/356wf2ar2j1y3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:46Z",
      "native_id": "10.64898/2026.10.14.754143",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.14.754143v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "ASD-FER: An Annotated Multi-Class Benchmark and Comparative Study for Facial Emotion Recognition in Children with Autism Spectrum Disorder",
  "title_text": "ASD-FER: An Annotated Multi-Class Benchmark and Comparative Study for Facial Emotion Recognition in Children with Autism Spectrum Disorder",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:46Z",
  "url": "https://research.draconitic.com/paper/356wf2ar2j1y3",
  "venue": "bioRxiv",
  "versions": []
}