SDGAN 《Semantics Disentangling for Text-to-Image Generation》探析
论文地址：https://arxiv.org/abs/1904.01480v1 收录于：CVPR 2019 这篇文章属于Text-to-Image一类，它所解决的主要任务是如何根据文本的描述生成相应的图像，不仅要求生成的图像要清晰真实，而且更要求其符合给定的文本描述。类似的GAN模型有StackGAN（《StackGAN:Text to Photo-realistic Image Synthesi
相关文章
- 1. ACL2020 Semantics-aware BERT for Language Understanding
- 2. RL for Sentence Generation
- 3. Adversarial Learning for Neural Dialogue Generation 代码分析
- 4. Review networks for caption generation
- 5. [ICCV2019] Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
- 6. Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
- 7. Graph R-CNN for Scene Graph Generation
- 8. Synchronous Bidirectional Inference for Neural Sequence Generation
- 9. Deep Reinforcement Learning for Dialogue Generation
- 10. Clang AST parsing for automated code generation
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • 互联网组织的未来：剖析GitHub员工的任性之源
- • 算法总结-深度优先算法
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. ACL2020 Semantics-aware BERT for Language Understanding
- 2. RL for Sentence Generation
- 3. Adversarial Learning for Neural Dialogue Generation 代码分析
- 4. Review networks for caption generation
- 5. [ICCV2019] Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
- 6. Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
- 7. Graph R-CNN for Scene Graph Generation
- 8. Synchronous Bidirectional Inference for Neural Sequence Generation
- 9. Deep Reinforcement Learning for Dialogue Generation
- 10. Clang AST parsing for automated code generation