ICMR 2018: Call for special session papers

Predicting User Perceptions of Multimedia Content

Understanding of multimedia content by machines has reached an important milestone in current research with the latest achievements in machine learning. However, although such technologies may enable a high level understanding of multimedia scenes, their output still remains a factual and plain description of it. What is related to human perceptions of media content is still most of the time eluded, although there have been important breakthroughs in analyzing subjective properties, such as aesthetics, memorability, or induced emotions.

Predicting user perceptions of multimedia content aims to go one step forward in putting human subjectivity and interpretation in the centre of the scene understanding, by rending the systems able to automatically predict human-like concepts such as interestingness, affective values and emotions, aesthetic values, memorability, novelty, complexity, visual composition and stylistic attributes, creativity, etc. These are specifically interesting for a very broad range of current applications, e.g., content retrieval and search, storytelling, targeted advertising, education and learning, and content filtering.

Work already exists in the literature that studies the psychological aspects of these notions or investigates potential correlations between two or more of these human concepts. Attempts at building computational models capable of predicting such notions can also be found, which use state-of-the-art machine learning techniques. Nevertheless their performance proves that there is still room for improvement, as the task is by its nature highly challenging and multifaceted because it has to address on one hand, the psychological implications of the human concepts, and on the other hand their translation to machines, meaning the availability of appropriate labeled data and specially tuned algorithms.

The ICMR 2018 Special Session “Predicting User Perceptions of Multimedia Content” is calling for papers (8 pages) presenting significant and innovative research focusing this topic. Papers should extend the state of the art by addressing new problems or proposing insightful solutions. We encourage submissions covering relevant perspectives in this area including:

• Data collection, annotation and evaluation methods
• Computational models for predicting user perceptions of multimedia content
• Retrieval and search models that incorporate prediction of user perceptions
• Content filtering and recommendation based on user perceptions of content
• Video segmentation and summarization based on user perceptions of content
• Deep learning models for predicting user perceptions of multimedia content
• Prediction and modeling of content interestingness and covariates
• Content-driven and social-driven interestingness prediction
• Influence of context on interestingness prediction
• Temporal computational models for capturing emotional changes along videos
• Applications of content understanding based on user perceptions

Maximum Length of a Paper

Each full paper should not be longer than 8 pages.

Important Dates

Paper Submission: February 17, 2018 Extended: February 25 at 23:59 EET
Notification of Acceptance: March 30, 2018
Camera-Ready Papers Due: April 27, 2018

Single-Blind Review

ICMR will use a single-blind review process for special session paper selection. Authors should provide author names and affiliations in their manuscript.

Abstract and Keywords

The abstract and the keywords form the primary source for assigning papers to reviewers. So make sure that they form a concise and complete summary of your paper with sufficient information to let someone who doesn’t read the full paper know what it is about.

Submission Instructions

See the ICMR 2018 Paper submission section.

Organizers

Claire-Hélène Demarty & Ngoc Q. K. Duong, Technicolor, France (contact person: claire-helene.demarty(at)technicolor.com)
Emmanuel Dellandrea, Ecole Centrale Lyon, France
Mats Sjöberg, Aalto University, Finland
Bogdan Ionescu, University Politehnica of Bucharest, Romania
Thanh-Toan Do, University of Adelaide, Australia
Yoann Baveye, Capacités, France