{
  "abstract": "Weakly supervised video anomaly detection remains a challenging problem, primarily due to the scarcity of abnormal training samples and the lack of diverse feature representations, which hamper the learning of discriminative models. To address these issues, we introduce a novel weakly supervised cross-domain framework that enriches feature representations by explicitly integrating semantic cues from Human-Object Interactions (HOI) and action dynamics. Specifically, we model domain-specific features using two independent encoders and fuse them via a bi-directional cross-attention mechanism to obtain a unified embedding. To further alleviate class imbalance and enhance feature discrimination, our network is jointly optimized with classification loss, a cross-domain contrastive loss, and a clip-level focal loss. The proposed method is evaluated with various visual backbones, demonstrating its adaptability and robustness. Extensive experiments show that our approach achieves competitive performance against state-of-the-art methods under weak supervision in terms of AUC. Specifically, our proposed method achieves 98.33% AUC and 87.96% AUC on two benchmark datasets, i.e., ShanghaiTech and UCF-Crime, respectively.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Artificial Intelligence, Universiti Malaya, Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia",
    "Engineering Cluster, Singapore Institute of Technology, Singapore, Singapore"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Maowen Zhou"
    },
    {
      "affs": [
        1
      ],
      "name": "Erma Rahayu Mohd Faizal Abdullah"
    },
    {
      "name": "Aznul Qalid Md Sabri"
    },
    {
      "name": "Susanto Rahardja"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6bgh6e0p4cytg.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0358538",
  "fulltext_url": null,
  "id": "6bgh6e0p4cytg",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0358538",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1702|Anomaly Detection Techniques and Applications"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Learning/Human learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Learning and memory/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Learning and memory/Learning/Human learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Learning/Human learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Computer and information sciences/Data management/Data visualization"
    ],
    [
      "plos",
      "/Medicine and health sciences/Epidemiology/Medical risk factors/Traumatic injury risk factors/Road traffic collisions"
    ],
    [
      "plos",
      "/Medicine and health sciences/Public and occupational health/Traumatic injury risk factors/Road traffic collisions"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Mathematical functions/Convolution"
    ],
    [
      "plos",
      "/Social sciences/Linguistics/Semantics"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Learning/Human learning"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Social sciences/Sociology/Social discrimination"
    ]
  ],
  "openalex": "W7213554626",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0358538&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-18",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/6bgh6e0p4cytg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:49Z",
      "native_id": "10.1371/journal.pone.0358538",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0358538"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Learn the interactions: Weakly supervised video anomaly detection with human-object interactions",
  "title_text": "Learn the interactions: Weakly supervised video anomaly detection with human-object interactions",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:49Z",
  "url": "https://research.draconitic.com/paper/6bgh6e0p4cytg",
  "venue": "PLOS One",
  "versions": []
}