nocaps: novel object captioning at scale

@article{Agrawal2019nocapsNO,
  title={nocaps: novel object captioning at scale},
  author={Harsh Agrawal and Karan Desai and Yufei Wang and Xinlei Chen and Rishabh Jain and Mark Johnson and Dhruv Batra and Devi Parikh and Stefan Lee and Peter Anderson},
  journal={International Conference on Computer Vision},
  year={2019},
  pages={8947-8956}
}
  • Harsh Agrawal, Karan Desai, +7 authors Peter Anderson
  • Published 2019
  • Computer Science
  • International Conference on Computer Vision
  • Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less supervision. To encourage the development of image captioning models that can learn visual concepts from alternative data sources, such as object detection datasets, we present the first large-scale… CONTINUE READING
    23 Citations
    VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training
    • 2
    • Highly Influenced
    • PDF
    Captioning Images with Novel Objects via Online Vocabulary Expansion
    Compositional Generalization in Image Captioning
    • 11
    • PDF
    Captioning Images Taken by People Who Are Blind
    • 9
    • Highly Influenced
    • PDF
    M2: Meshed-Memory Transformer for Image Captioning
    • 10
    • PDF
    Understanding Image Captioning Models beyond Visualizing Attention
    TextCaps: a Dataset for Image Captioning with Reading Comprehension
    • 4
    • PDF
    Meshed-Memory Transformer for Image Captioning
    • 21
    • PDF
    Say As You Wish: Fine-Grained Control of Image Caption Generation With Abstract Scene Graphs
    • 7
    • PDF

    References

    SHOWING 1-10 OF 59 REFERENCES
    Captioning Images with Diverse Objects
    • 92
    • PDF
    Partially-Supervised Image Captioning
    • 9
    • PDF
    Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
    • 173
    • Highly Influential
    • PDF
    Guided Open Vocabulary Image Captioning with Constrained Beam Search
    • 76
    • Highly Influential
    • PDF
    Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects
    • 76
    • PDF
    Decoupled Novel Object Captioner
    • 23
    • PDF
    Rich Image Captioning in the Wild
    • K. Tran, X. He, Lei Zhang, Jian Sun
    • Computer Science
    • 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
    • 2016
    • 84
    • PDF
    Neural Baby Talk
    • 188
    • Highly Influential
    • PDF
    From captions to visual concepts and back
    • 954
    • PDF