The sketchy database

By Patsorn Sangkloy, Nathan Burnell, Cusuh Ham, James Hays. 2016

327 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Tao A. Xiang
2. Alan L. Yuille
3. Luc Van Gool
4. Dacheng Tao
5. Yi-Zhe Song
6. Timothy M. Hospedales
7. Trevor Darrell
8. Xiaogang Wang

In ML Systems & Hardware

1. Wengling Chen
2. Eric P. Xing
3. Timothy M. Hospedales
4. Zachary Chase Lipton
5. James Hays

Citations in the corpus

• Learning Robust Global Representations by Penalizing Local Predictive Power (2019, methodology): “Inspired by the Sketch data of (Li et al., 2017a) with seven classes, and several other Sketch data sets, such as the Sketchy data set (Sangkloy et al., 2016) with 125 classes and the Quick Draw! data set (QuickDraw, 2018) with 345 classes, as well as motivated by the need of a large-scale sketch…”
• Sketch-Guided Object Localization in Natural Images (2020, background): “Despite the problem of sketch-guided object localization has a relation to the well-studied sketch-based image retrieval (SBIR) problem [5,14,20,25,28,30,38,40], these are distinctively different in terms of objectives.”
• Generalising Fine-Grained Sketch-Based Image Retrieval (2019, methodology): “Subsequent research has focused issues surrounding multi-branch deep learning methods that learn to extract comparable features from these heterogeneous domains [24, 36, 28, 22].”
• Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval (2019, methodology): “We evaluated SAKE on two large-scale sketchphoto datasets: TU-Berlin [5] and Sketchy [33] with extended images obtained from [44, 21].”
• Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval (2020, unknown): “While the other SBIR frameworks [49, 36] use triplet loss [45] in order to learn an embedding suited for comparing sketch and photo, we optimise the rank of the target photo with respect to a sketch query.”
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis (2018, methodology): “ [62] shows promising results on unsupervised image translation by enforcing cycle-consistency losses. 3. Sketchy Database Augmentation In this section, we discuss how we augment the Sketchy database [49] with Flickr images and synthesize edge maps which we hope approximate human sketches. The datas”