Guest Editorial: Challenges and Perspectives for Affective Analysis in Multimedia

  title={Guest Editorial: Challenges and Perspectives for Affective Analysis in Multimedia},
  author={M. Soleymani and Yi-Hsuan Yang and Go Irie and Alan Hanjalic},
  journal={IEEE Trans. Affect. Comput.},
THERE has been an increasing interest in the research on multimedia indexing and retrieval based on subjective concepts, such as emotion, preference and aesthetics. The research efforts in this direction are considered human-centered and beyond the conventional keywordor (semantic) object-based multimedia analysis paradigm [1]. In addition, the problems addressed by these efforts are considered challenging since they require multidisciplinary understanding of human behavior and perception as… 
Perceived emotion from images through deep neural networks
  • Alex Hernández-García
  • Computer Science
    2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)
  • 2017
New deep neural architectures suitable for affective content analysis are explored, together with semi-supervised models that help handle the relative lack of available data and the uncertainty and subjectivity of the annotations.
Special issue on affective design using big data
It is indicated that products with good affective design excite psychological feelings and improve consumer satisfaction in terms of emotional aspects and important affectiveneeds for newproductdevelopment may be partially or fully overlooked.
Affective rating of audio and video clips using the EmojiGrid
The results of this study show that for both sound and video, the agreement between the mean ratings obtained with the EmojiGrid and those obtained with an alternative and validated affective rating tool in previous studies in the literature, is excellent for valence and good for arousal.
Affective rating of audio and video clips using the EmojiGrid.
The results of this study show that for both sound and video, the agreement between the mean ratings obtained with the EmojiGrid and those obtained with an alternative and validated affective rating tool in previous studies in the literature, is excellent for valence and good for arousal.
An exploratory study on computer-aided affective product design based on crowdsourcing
A crowd-based experimental approach is demonstrated that establishes the correlations between human emotional responses described by bi-polar adjectives and design factors of a bag, and demonstrates the preliminary feasibility of improving Kansei Engineering applications with big data obtained from crowdsourcing.
Exploring the effects of emotional design and emotional intelligence in multimedia-based learning: an engineering educational perspective
This study replicated the methodology used in previous research studies in emotional design in multimedia learning by further exploring the gaps from those studies especially the effects of negative design, EI and a new sample that primarily focuses on engineering undergraduates in Malaysia.
Exploring the effects of visual aesthetics in e-learning for engineering students
e-Learning is changing the way students learn in the classroom. However, one of the least emphasised aspect in e-learning design concerns with aesthetics. Recent research in multimedia aesthetics
The Principle of Sharpening (I): Filtering. Cosmos Out of Chaos—Aspects and Elements of the Musical Materials
The compositional use of the partial-tone-spectrum as in Wagner’s Prelude to Rheingold is already a transition to crystallization, and the automated filtering by soft computing and FL-oriented methods is analysis of similarities.


Corpus Development for Affective Video Indexing
Three dimensions emerge as critical for affective video corpora, and form the basis for the proposed guidelines: the context of viewer response, personal variation among viewers, and the effectiveness and efficiency of corpus creation.
Assistive Image Comment Robot—A Novel Mid-Level Concept-Based Representation
Through user studies, it was showed machine suggested comments were accepted by users for online posting in 90 percent of completed user sessions, while very favorable results were also observed in various dimensions (plausibility, preference, and realism) when assessing the quality of the generated image comments.
Quantitative Study of Music Listening Behavior in a Social and Affective Context
This study shows that it is feasible to computationally model the latent structure underlying music listening and mood regulation, and shows that the association among user mood, music emotion, and individual's personality is identified.
Affective Computing
Key issues in affective computing, " computing that relates to, arises from, or influences emotions", are presented and new applications are presented for computer-assisted learning, perceptual information retrieval, arts and entertainment, and human health and interaction.
A supervised approach to movie emotion tracking
A database of movie affect, annotated in continuous time, on a continuous valence-arousal scale is developed and supervised learning methods are proposed to model the continuous affective response using hidden Markov Models (independent) in each dimension.
Hierarchical Dirichlet Process Mixture Model for Music Emotion Recognition
In the tasks of music emotion annotation and retrieval, experimental results show that the proposed MER system outperforms state-of-the-art systems in terms of F-score and mean average precision.
DECAF: MEG-Based Multimodal Database for Decoding Affective Physiological Responses
DECAF is presented, a detailed analysis of the correlations between participants' self-assessments and their physiological responses and single-trial classification results for valence, arousal and dominance are presented, with performance evaluation against existing data sets.
Autism Blogs: Expressed Emotion, Language Styles and Concerns in Personal and Community Settings
This work further investigates these online populations through the contents of not only their posts but also their comments, and finds all three features are found to be significantly different between Autism and Control, and between autism Personal and Community.
Consensus Analysis and Modeling of Visual Aesthetic Perception
A characteristic relation between skewness and kurtosis of aesthetic score distributions in a massive photo aesthetics dataset generated from online voting is reported, supporting the necessity of a consensus property in addition to the preference used so far for accurate modeling of aesthetic evaluation process in human mind.
Modeling Emotion Influence in Image Social Networks
It is found that more social interactions correlate with higher emotion influence between two users, and the influence of negative emotions is stronger than positive ones.