BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography

@article{Wilber2017BAMTB,
  title={BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography},
  author={Michael J. Wilber and Chen Fang and Hailin Jin and Aaron Hertzmann and John P. Collomosse and Serge J. Belongie},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1211-1220}
}
Computer vision systems are designed to work well within the context of everyday photography. [] Key Method First, we collect a large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists. We annotate Behance imagery with rich attribute labels for content, emotions, and artistic media. Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of…
Photozilla: A Large-Scale Photography Dataset and Visual Embedding for 20 Photography Styles
TLDR
A novel Siamese-based network is presented that uses the trained classification models as the base architecture to adapt and classify unseen styles with only 25 training samples and reports an accuracy of over 68% for identifying 10 other distinct types of photography styles.
Artistic Object Recognition by Unsupervised Style Adaptation
TLDR
This paper proposes a method for recognizing objects in artistic modalities (such as paintings, cartoons, or sketches), without requiring any labeled data from those modalities, and explicitly accounts for stylistic domain shifts between and within domains.
Image Representations for Style Retrieval, Recognition and Background Replacement Tasks
  • Computer Science
  • 2020
TLDR
This work proposes a data-driven approach to sky-replacement that avoids color correction by finding a diverse set of skies that are consistent in color and natural illumination with the query image foreground and proposes an unsupervised protocol for learning a neural embedding of visual style of images.
Artistic Domain Generalisation Methods are Limited by their Deep Representations
TLDR
It is shown that fixing the last layer of AlexNet to random values provides a performance comparable to state of the art DA and DG algorithms, when tested over the PACS benchmark, and concludes that texture alone is insufficient to support generalisation.
Matching Faces and Attributes Between the Artistic and the Real Domain: the PersonArt Approach
TLDR
The proposed algorithm for retrieving similar faces between the artistic and the real domain is implemented in a real showcase at the Gallerie Estensi museum in Italy, with the participation of more than 1,100 visitors in just three days.
Artsheets for Art Datasets
TLDR
A checklist of questions customized for use with art datasets is provided in order to help guide assessment of the ways that dataset design may either perpetuate or shift exclusions found in repositories of art data.
Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings
TLDR
It is demonstrated that several GNN architectures can outperform strong CNN baselines in a range of fine art analysis tasks, such as style classification, artist attribution, creation period estimation, and tag prediction, while training them requires an order of magnitude less computational time and only a small amount of labeled data.
A Style-Aware Content Loss for Real-time HD Style Transfer
TLDR
A style-aware content loss is proposed, which is trained jointly with a deep encoder-decoder network for real-time, high-resolution stylization of images and videos and results show that this approach better captures the subtle nature in which a style affects content.
A Dataset and a Convolutional Model for Iconography Classification in Paintings
TLDR
A novel paintings data set for iconography classification is introduced and the quantitative and qualitative results of applying a Convolutional Neural Network (CNN) classifier to the recognition of the iconography of artworks are presented.
...
...

References

SHOWING 1-10 OF 38 REFERENCES
High level describable attributes for predicting aesthetics and interestingness
TLDR
This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections and demonstrates that an aesthetics classifier trained on describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments.
Recognizing Image Style
TLDR
An approach to predicting style of images, and a thorough evaluation of different image features for these tasks, find that features learned in a multi-layer network generally perform best -- even when trained with object class (not style) labels.
AVA: A large-scale database for aesthetic visual analysis
TLDR
A new large-scale database for conducting Aesthetic Visual Analysis: AVA, which contains over 250,000 images along with a rich variety of meta-data including a large number of aesthetic scores for each image, semantic labels for over 60 categories as well as labels related to photographic style is introduced.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene
Towards Category-Based Aesthetic Models of Photographs
TLDR
A novel set of image segmentation methods based on feature contrast are introduced, such that luminance, sharpness, saliency, color chroma, and a measure of region relevance are computed to generate different image partitions.
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
TLDR
This work proposes to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop, and constructs a new image dataset, LSUN, which contains around one million labeled images for each of 10 scene categories and 20 object categories.
Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
TLDR
This paper proposes an algorithm to decouple the human reporting bias from the correct visually grounded labels, and shows significant improvements over traditional algorithms for both image classification and image captioning, doubling the performance of existing methods in some cases.
Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark
TLDR
A new data set is introduced, which started from 3+ million weakly labeled images of different emotions and ended up 30 times as large as the current largest publicly available visual emotion data set, to encourage further research on visual emotion analysis.
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
TLDR
This work introduces an alternative approach, leveraging free, noisy data from the web and simple, generic methods of recognition, and demonstrates its efficacy on four fine-grained datasets, greatly exceeding existing state of the art without the manual collection of even a single label.
Collaborative feature learning from social media
TLDR
This paper proposes a new data-driven feature learning paradigm which does not rely on category labels and learns from user behavior data collected on social media, and finds that the learned feature significantly outperforms the state-of-the-art image features in learning better image similarities.
...
...