[
  {
    "id": "dl-08-1",
    "type": "paper-conference",
    "title": "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale",
    "author": [
      {
        "given": "Alexey",
        "family": "Dosovitskiy"
      },
      {
        "given": "Lucas",
        "family": "Beyer"
      },
      {
        "given": "Alexander",
        "family": "Kolesnikov"
      },
      {
        "given": "Dirk",
        "family": "Weissenborn"
      },
      {
        "given": "Xiaohua",
        "family": "Zhai"
      },
      {
        "given": "Thomas",
        "family": "Unterthiner"
      },
      {
        "given": "Mostafa",
        "family": "Dehghani"
      },
      {
        "given": "Matthias",
        "family": "Minderer"
      },
      {
        "given": "Georg",
        "family": "Heigold"
      },
      {
        "given": "Sylvain",
        "family": "Gelly"
      },
      {
        "given": "Jakob",
        "family": "Uszkoreit"
      },
      {
        "given": "Neil",
        "family": "Houlsby"
      }
    ],
    "container-title": "International Conference on Learning Representations",
    "issued": {
      "date-parts": [
        [
          2021
        ]
      ]
    },
    "DOI": "",
    "URL": "https://arxiv.org/abs/2010.11929"
  },
  {
    "id": "dl-08-2",
    "type": "paper-conference",
    "title": "Training data-efficient image transformers & distillation through attention",
    "author": [
      {
        "given": "Hugo",
        "family": "Touvron"
      },
      {
        "given": "Matthieu",
        "family": "Cord"
      },
      {
        "given": "Matthijs",
        "family": "Douze"
      },
      {
        "given": "Francisco",
        "family": "Massa"
      },
      {
        "given": "Alexandre",
        "family": "Sablayrolles"
      },
      {
        "given": "Hervé",
        "family": "Jégou"
      }
    ],
    "container-title": "Proceedings of the 38th International Conference on Machine Learning",
    "issued": {
      "date-parts": [
        [
          2021
        ]
      ]
    },
    "DOI": "",
    "URL": "https://proceedings.mlr.press/v139/touvron21a.html"
  },
  {
    "id": "dl-08-3",
    "type": "article",
    "title": "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows",
    "author": [
      {
        "given": "Ze",
        "family": "Liu"
      },
      {
        "given": "Yutong",
        "family": "Lin"
      },
      {
        "given": "Yue",
        "family": "Cao"
      },
      {
        "given": "Han",
        "family": "Hu"
      },
      {
        "given": "Yixuan",
        "family": "Wei"
      },
      {
        "given": "Zheng",
        "family": "Zhang"
      },
      {
        "given": "Stephen",
        "family": "Lin"
      },
      {
        "given": "Baining",
        "family": "Guo"
      }
    ],
    "container-title": "arXiv",
    "issued": {
      "date-parts": [
        [
          2021
        ]
      ]
    },
    "DOI": "10.48550/arXiv.2103.14030",
    "URL": "https://arxiv.org/abs/2103.14030"
  }
]
