Corpus ID: 237635145

Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poems

@article{Li2021Paint4PoemAD,
  title={Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poems},
  author={Dan Li and Shuai Wang and Jie Zou and Chang Tian and Elisha Nieuwburg and Fengyuan Sun and E. Kanoulas},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.11682}
}
  • Dan Li, Shuai Wang, +4 authors E. Kanoulas
  • Published 23 September 2021
  • Computer Science
  • ArXiv
In this work we propose a new task – artistic visualization of classical Chinese poems, where the goal is to generate paintings of a certain artistic style for classical Chinese poems. For this purpose, we construct a new dataset called Paint4Poem. The first part of Paint4Poem consists of 301 high-quality poem-painting pairs collected manually from an influential modern Chinese artist Feng Zikai. As its small scale poses challenges for effectively training poem-to-painting generation models, we… Expand

References

SHOWING 1-10 OF 47 REFERENCES
How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks
TLDR
This is the first work attempting to generate classical Chinese poetry from images with neural networks and a comprehensive experimental investigation with both human evaluation and quantitative analysis demonstrates that the proposed model can generate poems which convey images accurately. Expand
Image Inspired Poetry Generation in XiaoIce
TLDR
A system of poetry generation from images to mimic the process, which first extracts a few keywords representing objects and sentiments perceived from the image, then expands to related ones based on their associations in human written poems. Expand
A Multi-Modal Chinese Poetry Generation Model
TLDR
A three-stage multi-modal Chinese poetry generation approach which can effectively capture character, phrase, and sentence information between contexts and improve the symmetry delivered in poems is proposed. Expand
Sentiment-Controllable Chinese Poetry Generation
TLDR
Experimental results show the proposed novel semi-supervised conditional Variational Auto-Encoder model can control the sentiment of not only a whole poem but also each line, and improve the poetry diversity against the state-of-the-art models without losing quality. Expand
Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training
TLDR
This paper forms the task of poem generation into two correlated sub-tasks by multi-adversarial training via policy gradient, through which the cross-modal relevance and poetic language style can be ensured. Expand
Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System
TLDR
Jiuge is proposed, a human-machine collaborative Chinese classical poetry generation system that allows users to revise the unsatisfied parts of a generated poem draft repeatedly and allows constant and active participation of users in poetic creation. Expand
Images2Poem: Generating Chinese Poetry from Image Streams
TLDR
An Images2Poem model with a selection mechanism and an adaptive self-attention mechanism for the new multimedia task of generating classical Chinese poetry from image streams that outperforms baselines in different human evaluation metrics. Expand
Chinese Poetry Generation with Recurrent Neural Networks
TLDR
A model for Chinese poem generation based on recurrent neural networks which is ideally suited to capturing poetic content and form is proposed which outperforms competitive Chinese poetry generation systems using both automatic and manual evaluation methods. Expand
MirrorGAN: Learning Text-To-Image Generation by Redescription
TLDR
Thorough experiments on two public benchmark datasets demonstrate the superiority of MirrorGAN over other representative state-of-the-art methods. Expand
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
TLDR
An Attentional Generative Adversarial Network that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation and for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image. Expand
...
1
2
3
4
5
...