Corpus ID: 9996719

Generating Images from Captions with Attention

@article{Mansimov2016GeneratingIF,
  title={Generating Images from Captions with Attention},
  author={Elman Mansimov and Emilio Parisotto and Jimmy Ba and R. Salakhutdinov},
  journal={CoRR},
  year={2016},
  volume={abs/1511.02793}
}
  • Elman Mansimov, Emilio Parisotto, +1 author R. Salakhutdinov
  • Published 2016
  • Mathematics, Computer Science
  • CoRR
  • Motivated by the recent progress in generative models, we introduce a model that generates images from natural language descriptions. [...] Key Result We demonstrate that our model produces higher quality samples than other approaches and generates images with novel scene compositions corresponding to previously unseen captions in the dataset.Expand Abstract
    Generating Image Sequence from Description with LSTM Conditional GAN
    6
    Generative Adversarial Text to Image Synthesis
    1453
    ChatPainter: Improving Text to Image Generation using Dialogue
    40
    Learning Visually Grounded Sentence Representations
    32
    Image Generation from Caption
    Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
    3
    A Semi-supervised Framework for Image Captioning
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES
    Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
    4935
    Show and tell: A neural image caption generator
    3302
    DRAW: A Recurrent Neural Network For Image Generation
    1304
    Deep Visual-Semantic Alignments for Generating Image Descriptions
    1434
    Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
    1412
    Skip-Thought Vectors
    1448
    Unsupervised Learning of Video Representations using LSTMs
    1382
    Microsoft COCO: Common Objects in Context
    9678
    Multimodal Neural Language Models
    485