Summary of Style-based Clustering Of Visual Artworks and the Play Of Neural Style-representations, by Abhishek Dangeti et al.
Style-based Clustering of Visual Artworks and the Play of Neural Style-Representations
by Abhishek Dangeti, Pavan Gajula, Vivek Srivastava, Vikram Jamwal
First submitted to arxiv on: 12 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Clustering artworks based on style can have many potential real-world applications like art recommendations, style-based search and retrieval, and the study of artistic style evolution of an artist or in an artwork corpus. The paper introduces and explores the notion of ‘Style-based clustering of visual artworks’, arguing that this problem is largely unaddressed. To tackle this challenge, the authors devise different neural feature representations from various sources, including style-classification, style-transfer, and large language vision models. These features are then used for style-based clustering, which is evaluated through qualitative and quantitative analysis on multiple artwork corpora and synthetically styled datasets. The paper provides a broad framework for style-based clustering and evaluation, as well as insights into feature representations, architectures, and implications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Style-based clustering of artworks can have many practical uses, like recommending art styles or searching for similar artworks. This paper talks about how we can group artworks based on their style. The authors think that this is an important problem to solve because it’s not been done much before. They come up with different ways to represent artwork features using neural networks and then test these methods to see which ones work best. This helps us understand how to better cluster artworks by style, which can be useful in many areas. |
Keywords
» Artificial intelligence » Classification » Clustering » Style transfer
