Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A. Shamma, Michael S. Bernstein, Li Fei-Fei. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. International Journal of Computer Vision, 123(1):32-73, 2017. [doi]

@article{KrishnaZGJHKCKL17,
  title = {Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations},
  author = {Ranjay Krishna and Yuke Zhu and Oliver Groth and Justin Johnson and Kenji Hata and Joshua Kravitz and Stephanie Chen and Yannis Kalantidis and Li-Jia Li and David A. Shamma and Michael S. Bernstein and Li Fei-Fei},
  year = {2017},
  doi = {10.1007/s11263-016-0981-7},
  url = {https://doi.org/10.1007/s11263-016-0981-7},
  researchr = {https://researchr.org/publication/KrishnaZGJHKCKL17},
  cites = {0},
  citedby = {0},
  journal = {International Journal of Computer Vision},
  volume = {123},
  number = {1},
  pages = {32-73},
}