Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

@inproceedings{Jia2020FashionpediaOS,
  title={Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset},
  author={Menglin Jia and Mengyun Shi and M. Sirotenko and Yin Cui and Claire Cardie and Bharath Hariharan and Hartwig Adam and Serge J. Belongie},
  booktitle={ECCV},
  year={2020}
}
In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorization (recognize one or multiple attributes). The proposed task requires both localizing an object and describing its properties. To illustrate the various aspects of this task, we focus on the domain of fashion and introduce Fashionpedia as a step toward mapping out the visual aspects of… Expand
From Culture to Clothing: Discovering the World Events Behind A Century of Fashion Images
FITNet: Identifying Fashion Influencers on Twitter
FashionGraph: Understanding fashion data using scene graph generation
Instagram Filter Removal on Fashionable Images

References

SHOWING 1-10 OF 89 REFERENCES
Automatic Spatially-Aware Fashion Concept Discovery
The iMaterialist Fashion Attribute Dataset
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Relative attributes
IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Things
Microsoft COCO: Common Objects in Context
Panoptic Segmentation
Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network
LVIS: A Dataset for Large Vocabulary Instance Segmentation
ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations
...
1
2
3
4
5
...