Corpus ID: 32746326

Deep Learning for Identifying Potential Conceptual Shifts for Co-creative Drawing

@article{Karimi2018DeepLF,
  title={Deep Learning for Identifying Potential Conceptual Shifts for Co-creative Drawing},
  author={Pegah Karimi and Nicholas M. Davis and Kazjon Grace and Mary Lou Maher},
  journal={ArXiv},
  year={2018},
  volume={abs/1801.00723}
}
We present a system for identifying conceptual shifts between visual categories, which will form the basis for a co-creative drawing system to help users draw more creative sketches. The system recognizes human sketches and matches them to structurally similar sketches from categories to which they do not belong. This would allow a co-creative drawing system to produce an ambiguous sketch that blends features from both categories. 
Deep Learning in a Computational Model for Conceptual Shifts in a Co-Creative Design System
TLDR
The paper presents the results of a user study showing that increasing novelty in the AI contribution is associated with higher creative outcomes, whereas low novelty leads to less creative outcomes. Expand
Relating Cognitive Models of Design Creativity to the Similarity of Sketches Generated by an AI Partner
TLDR
The findings show that how similar the computational agent's sketch is to the user's original sketch is related to the presence of three types of design creativity in the users' response: combinatorial, exploratory, and transformational. Expand
Paper Dreams: Real-Time Human and Machine Collaboration for Visual Story Development
​Increasing human potential is the underlying incentive for all technological advances. In creativity, technology can be used to facilitate faster design and construction, to improve human creativeExpand
SmartPaint: a co-creative drawing system based on generative adversarial networks
TLDR
SmartPaint is developed, a co-creative drawing system based on generative adversarial networks (GANs), enabling a machine and a human being to collaborate in cartoon landscape painting. Expand
collabdraw: An Environment for Collaborative Sketching with an Artificial Agent
TLDR
A web-based environment for collaborative sketching of everyday visual concepts is presented and the integration of an artificial agent, instantiated as a recurrent neural network, who is both cooperative and responsive to actions performed by its human collaborator is explored. Expand
Evaluating Creativity in Computational Co-Creative Systems
TLDR
It is concluded that existing co-Creative systems tend to focus on evaluating the user experience, and adopting evaluation methods from autonomous creative systems may lead to co-creative systems that are self-aware and intentional. Expand

References

SHOWING 1-8 OF 8 REFERENCES
A Neural Representation of Sketch Drawings
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundredsExpand
Empirically Studying Participatory Sense-Making in Abstract Drawing with a Co-Creative Cognitive Agent
TLDR
The Drawing Apprentice system, designed to improvise and collaborate on abstract sketches with users in real time, qualifies as a new genre of creative technologies termed "casual creators" that are meant to creatively engage users and provide enjoyable creative experiences rather than necessarily helping users make a higher quality creative product. Expand
The Way We Think: Conceptual Blending and the Mind''s Hidden Complexities. Basic Books
A long-awaited synthesis that marks a major turning point in cognitive science. . Until recently, cognitive science focused on such mental functions as problem solving, grammar, and pattern-theExpand
The importance of drawing in the mechanical design process
TLDR
Five hypotheses, focused on the types of drawings, their necessity in mechanical problem solving, and their relation to the external representation medium, are presented and supported. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
ImageNet: A large-scale hierarchical image database
The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data.Expand
Visualizing Large-scale and High-dimensional Data
TLDR
The LargeVis is proposed, a technique that first constructs an accurately approximated K-nearest neighbor graph from the data and then layouts the graph in the low-dimensional space and easily scales to millions of high-dimensional data points. Expand
Deep Learning