{
  "id": "showattendtell2015",
  "title": "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention",
  "authors": [
    {
      "given": "Kelvin",
      "family": "Xu"
    },
    {
      "given": "Jimmy Lei",
      "family": "Ba"
    },
    {
      "given": "Ryan",
      "family": "Kiros"
    },
    {
      "given": "Kyunghyun",
      "family": "Cho"
    },
    {
      "given": "Aaron",
      "family": "Courville"
    },
    {
      "given": "Ruslan",
      "family": "Salakhutdinov"
    },
    {
      "given": "Richard S.",
      "family": "Zemel"
    },
    {
      "given": "Yoshua",
      "family": "Bengio"
    }
  ],
  "year": 2015,
  "venue": "ICML 2015",
  "paper_url": "https://proceedings.mlr.press/v37/xuc15.html",
  "pdf_url": "https://proceedings.mlr.press/v37/xuc15.pdf",
  "summary": "Introduces deterministic soft and stochastic hard visual attention for image captioning.",
  "connection": "An early stochastic-attention reference for the distinction between expected features and sampled selection.",
  "bibtex_type": "inproceedings",
  "citation_key": "xu2015show",
  "source_urls": [
    "https://proceedings.mlr.press/v37/xuc15.pdf",
    "https://arxiv.org/abs/1502.03044"
  ],
  "arxiv_id": "1502.03044",
  "arxiv_first_posted": "2015-02-10",
  "updated_at": "2026-11-10",
  "record_url": "https://yuntiandeng.com/research/papers/showattendtell2015/"
}