Workshop on AI Aesthetics in Art and Media

2-6 December 2018
Perth Western Australia

Call for Paper

Aesthetics relates to the subjective notion of art, beauty and taste. The advancement of digital technologies, particularly the explosive growth in mobile devices, the expansion of social media and further digitization of artworks, have spurred on a rapidly growing interest in the field of "computational aesthetics". With the large amount of artistic media content (artworks, photographs, video) readily available, there arises a need for intelligent analysis and prediction of aesthetics, and other associated concepts such as interestingness, popularity, and viralness of media content. In addition, recent advances in machine learning, artificial intelligence and multimedia technologies are transforming the way artistic media content are generated and manipulated. Automatic generation of photo-realistic art, enhancement and manipulation of media content, and transfer of artistic styles from artworks to images/videos, are now real possibilities.

This workshop aims to bring together individuals with technical experience of using computer-based techniques such as machine learning, artificial intelligence and multimedia technologies to solve a variety of problems, ranging from automatic analysis and understanding of aesthetics in media content (artworks, photographs, videos) to aesthetics-driven content generation and synthesis. The scope of this workshop includes, but is not limited to:

  • understanding, analysis and prediction of media aesthetics, and associated concepts such as interestingness, popularity, and viralness
  • deep learning techniques for aesthetics understanding
  • analysis and prediction of image (paintings, photographs) style and saliency
  • artistic style transfer from artworks to images
  • aesthetic-based enhancement and manipulation of media
  • aesthetic-driven generative art and design
  • aesthetics in social media networks
  • non-photorealistic rendering
  • sketching and content simplification techniques
  • aesthetics based visualizations

Important dates

Paper Submission due
Sep. 27, 2018 Oct. 10, 2018
Oct. 18, 2018 Oct. 22, 2018
Camera-ready paper deadline
Nov. 1, 2018
Workshop Dates
Dec. 2-3, 2018
Main Conference Dates
Dec. 4-6, 2018

Paper Submission

The workshop paper format should follow the guideline for paper submission in ACCV2018 (see

  • All submissions will be handled electronically via the workshop's CMT Website.
    Click the link to go to the submission site
  • Example paper submission with detailed instructions: accv2018submission.pdf LaTeX Templates (zip):
  • A complete paper should be submitted using the above templates, which are blind-submission review-formatted templates.
  • The submission page length is 14 pages for content plus maximum two pages for references. Papers which violate these page limits will be rejected without review.
The new paper submission deadline is: Obtober 10, 2018.

Camera Ready Submission
All camera ready submission, together with the signed ACCV Workshops Copyright form are to be submitted to the AIAM Workshop's CMT Website.

For detailed instruction on preparing the camera ready submission, please refer the Camera Ready Submission Instruction at the main conference, ACCV 2018 website.

The camera ready submission deadline is: November 1, 2018. The AIAM workshop proceeding will be published together with the ACCV 2018 proceedings by Springer, in the LNCS series (Lecture Notes in Computer Science).

For each paper, at least one author has to be registered for attending the workshop / conference by the camera ready deadline (November 1, 2018). Without a valid registration at the workshop / conference by the deadline, your paper will not be published. Papers that arrive after the deadline may not appear on the conference LNCS proceedings and may not be placed in Springerlink.

The workshop registration will be handled as part of the main conference registration.

Invited Talks

Alan Blair

University of New South Wales

Title: Adversarial Deep Learning for Computational Creativity


This talk will briefly summarize both historical and recent developments in adversarial and convolutionary machine learning - including virtual creatures, sorting networks and game playing, as well as computational creativity. Recent work in artist-critic convolution will be described, in which a genetic program artist trained by hierarchical evolution contends with a deep convolutional neural network critic trained by gradient descent. Driven by selective pressure for low algorithmic complexity, combined with the need to fool the critic, the artist evolves to produce geometric shapes and patterns which remind us of everyday objects, landscapes and designs in a manner comparable to abstract art of the early 20th Century. The talk will conclude with a discussion of recent developments in the field, and possible future directions.


Alan Blair completed his PhD at MIT and worked at Brandeis, University of Queensland and University of Melbourne, before taking up his current position at UNSW. His research interests include self learning for strategic games, robot navigation, language processing, convolutional network architectures and training, adversarial and coevolutionary dynamics, multi-task learning, hierarchical evolution and computational creativity.

Program (3rd Decemebr 2018)

02:00 pm - 02:10 pm
Opening Address
02.10 pm - 03:30 pm
Invited Talk
03:30 pm - 04:00 pm
Coffee break
04:00 pm - 05:20 pm
Oral presentations
05:20 pm - 05:30 pm
Closing Remarks

Oral Presentation

04:00 pm - 04:20 pm
Let AI Clothe You: Diversified Fashion Generation
04:20 pm - 04:40 pm
Word-Conditioned Image Style Transfer
04:40 pm - 05:00 pm
Paying Attention to Style: Recognizing Photo Styles with Convolutional Attentional Units
05:00 pm - 05:20 pm
Font Style Transfer Using Neural Style Transfer


Wen-Huang Cheng

National Chiao Tung University, Taiwan

Wei-Ta Chu

National Chung Cheng University, Taiwan

John See

Multimedia University, Malaysia

Lai-Kuan Wong

Multimedia University, Malaysia