2601.16155v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "06e45117af9e702cf7b36adad8092fd7ea632140facf5917cf5469bf83ee7912",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.16155v1.pdf",
      "size": 1637807
    },
    "source": {
      "execution_id": "566c46d0-3813-4b63-9421-c727763c2f53",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 5,
      "producer": "pikepdf 8.15.1",
      "title": "HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval",
      "version": "1.7"
    },
    "source": {
      "execution_id": "e2148008-0d76-46f6-bfae-9dff7085f070",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}