Corpus ID: 231662219

DAF: re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition

@article{Rios2021DAFRA,
  title={DAF: re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition},
  author={Edwin Arkel Rios and W. Cheng and Bo-Cheng Lai},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.08674}
}
In this work we tackle the challenging problem of anime character recognition. Anime, referring to animation produced within Japan and work derived or inspired from it. For this purpose we present DAF:re (DanbooruAnimeFaces:revamped), a large-scale, crowd-sourced, long-tailed dataset with almost 500 K images spread across more than 3000 classes. Additionally, we conduct experiments on DAF:re and similar datasets using a variety of classification models, including CNN based ResNets and self… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 23 REFERENCES
Image Transformer
  • 246
  • PDF
Cartoon Face Recognition: A Benchmark Dataset
  • 2
  • PDF
Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
  • 86
  • PDF
Transformers in Vision: A Survey
  • 15
  • PDF
Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
  • 69
  • PDF
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • 222
  • PDF
Attention is All you Need
  • 17,099
  • PDF
Sketch-Based Manga Retrieval Using Deep Features
  • 8
Sketch-based manga retrieval using manga109 dataset
  • 273
  • PDF
Deep Residual Learning for Image Recognition
  • 62,694
  • Highly Influential
  • PDF
...
1
2
3
...