2019 · 98 citations · 33 references
ComputingComputer ScienceComputer VisionGenerative ArtNatural Language ProcessingLanguage ModelingNatural Language GenerationScene CompositionScene ConstructionText GenerationGenerative Adversarial NetworksGenerative Image SynthesisInterpretable Neural NetworksNatural Language InterfacesSequence-to-sequence GenerationVisual Scene Description
In this paper, we propose Text2Scene, a model that generates various forms of compositional scene representations from natural language descriptions. Unlike recent works, our method does NOT use Generative Adversarial Networks (GANs). Text2Scene instead learns to sequentially generate objects and their attributes (location, size, appearance, etc) at every time step by attending to different parts of the input text and the current status of the generated scene. We show that under minor modifications, the proposed framework can handle the generation of different forms of scene representations, including cartoon-like scenes, object layouts corresponding to real images, and synthetic images. Our method is not only competitive when compared with state-of-the-art GAN-based methods using automatic metrics and superior based on human judgments but also has the advantage of producing interpretable results.
33
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever, Oriol Vinyals, Quoc V. Le · arXiv (Cornell University) · 2014 · 13.4K citations · Full text
Computing, Computer Science, French +14
FaceNet: A unified embedding for face recognition and clustering
2015 · 11.2K citations · Full text