{
  "annotation_id": "51784efa-d11f-44ba-aeb4-75de54113bc5",
  "date_created": "2026-02-17T05:53:19.947000Z",
  "date_modified": "2026-02-17T05:53:19.947000Z",
  "file_hash": "614ae21d9a9c763e03fa792a2bd002f9ca27a7d04039679bded119f2b9bf573f",
  "private": false,
  "record": {
    "abstract": "Egocentric Human-Object Interaction (EHOI) analysis is crucial for industrial safety, yet the development of robust models is hindered by the scarcity of annotated domain-specific data. We address this challenge by introducing a data generation framework that combines synthetic data with a diffusion-based process to augment real-world images with realistic Personal Protective Equipment (PPE). We present GlovEgo-HOI, a new benchmark dataset for industrial EHOI, and GlovEgo-Net, a model integrating Glove-Head and Keypoint- Head modules to leverage hand pose information for enhanced interaction detection. Extensive experiments demonstrate the effectiveness of the proposed data generation framework and GlovEgo-Net. To foster further research, we release the GlovEgo-HOI dataset, augmentation pipeline, and pre-trained models at: GitHub project.",
    "arxiv_id": "2601.09528",
    "authors": [
      "Alfio Spoto",
      "Rosario Leonardi",
      "Francesco Ragusa",
      "Giovanni Maria Farinella"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "GlovEgo-HOI: Bridging the Synthetic-to-Real Gap for Industrial Egocentric Human-Object Interaction Detection",
    "url": "https://arxiv.org/abs/2601.09528",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "3c64859f-27d1-45da-a03b-a42e9cbd1ed8",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}