Aligning Where to See and What to Tell: Image Captioning with Region-Based Attention and Scene-Specific Contexts

Kun Fu, Junqi Jin, Runpeng Cui, Fei Sha, Changshui Zhang. Aligning Where to See and What to Tell: Image Captioning with Region-Based Attention and Scene-Specific Contexts. IEEE Trans. Pattern Anal. Mach. Intell., 39(12):2321-2334, 2017. [doi]

@article{FuJCSZ17,
  title = {Aligning Where to See and What to Tell: Image Captioning with Region-Based Attention and Scene-Specific Contexts},
  author = {Kun Fu and Junqi Jin and Runpeng Cui and Fei Sha and Changshui Zhang},
  year = {2017},
  doi = {10.1109/TPAMI.2016.2642953},
  url = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2016.2642953},
  researchr = {https://researchr.org/publication/FuJCSZ17},
  cites = {0},
  citedby = {0},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  volume = {39},
  number = {12},
  pages = {2321-2334},
}