Affective Level Video Segmentation by Utilizing the Pleasure-Arousal-Dominance Information

M.Kom., Agus Zainal Arifin, S.Kom.,; Cheung, Peter

doi:10.1109/tmm.2008.2004911

Cited by 48 publications

(33 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Affective video content analysis aims to automatic emotion recognition with applications in mood-based personalized content delivery, video indexing, and summarization [61,62], and ground truth data is needed both for training and benchmarking. The HUMAINE database [63], consisting of 50 clips from 1.5-3 min, is annotated with a wide range of labels, i.e., emotion-related states (intensity, arousal, valence, etc.…”

Section: Emotion Datasetsmentioning

confidence: 99%

COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization

Zlatintsi

Koutras

Evangelopoulos

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

Research related to computational modeling for machine-based understanding requires ground truth data for training, content analysis, and evaluation. In this paper, we present a multimodal video database, namely COGNIMUSE, annotated with sensory and semantic saliency, events, cross-media semantics, and emotion. The purpose of this database is manifold; it can be used for training and evaluation of event detection and summarization algorithms, for classification and recognition of audio-visual and cross-media events, as well as for emotion tracking. In order to enable comparisons with other computational models, we propose state-of-the-art algorithms, specifically a unified energy-based audio-visual framework and a method for text saliency computation, for the detection of perceptually salient events from videos. Additionally, a movie summarization system for the automatic production of summaries is presented. Two kinds of evaluation were performed, an objective based on the saliency annotation of the database and an extensive qualitative human evaluation of the automatically produced summaries, where we investigated what composes high-quality movie summaries, where both methods verified the appropriateness of the proposed methods. The annotation of the database and the code for the summarization system can be found at

show abstract

Section: Emotion Datasetsmentioning

confidence: 99%

COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization

Zlatintsi

Koutras

Evangelopoulos

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…Thus, we are motivated to study modality fusion strategies that may benefit induced emotion recognition. In addition, the LSTM model has low performance for predicting movie induced emotions [31], 2 yet it has achieved leading performance in various emotion recognition tasks due to its ability to model temporal context (e.g. [32]).…”

Section: Previous Work On Liris-accede Databasementioning

confidence: 99%

“…Recently, increased attention has been paid to recognizing emotions in spectators induced by affective content due to potential applications, such as emotion-based content delivery [1] or video indexing and summarization [2]. However, recognizing the emotions induced by affective content remains a challenging task, with only weak to moderate correlations achieved between automatic predictions and human annotations [3].…”

Section: Introductionmentioning

confidence: 99%

Recognizing induced emotions of movie audiences: Are induced and perceived emotions the same?

Tian

Muszyński

Lai

et al. 2017

2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)

View full text Add to dashboard Cite

Abstract-Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.

show abstract

“…Their training data consisted of 36 full-length popular Hollywood movies divided into 2040 scenes. Arifin and Cheung [10] based their framework on a hierarchical-coupled dynamic Bayesian network to model the dependencies between the Potential-Arousal-Dominance (PAD) dimensions. This model takes into consideration the influence of former emotional events.…”

Section: B Emotional Classificationmentioning

confidence: 99%

A Large Video Database for Computational Models of Induced Emotion

Baveye

Bettinelli

Dellandréa

et al. 2013

2013 Humaine Association Conference on Affective Computing and Intelligent Interaction

View full text Add to dashboard Cite

International audienceTo contribute to the need for emotional databases and affective tagging, the LIRIS-ACCEDE is proposed in this paper. LIRIS-ACCEDE is an Annotated Creative Commons Emotional DatabasE composed of 9800 video clips extracted from 160 movies shared under Creative Commons licenses. It allows to make this database publicly available1 without copyright issues. The 9800 video clips (each 8-12 seconds long) are sorted along the induced valence axis, from the video perceived the most negatively to the video perceived the most positively. The annotation was carried out by 1518 annotators from 89 different countries using crowdsourcing. A baseline late fusion scheme using ground truth from annotations is computed to predict emotion categories in video clips

show abstract

Affective Level Video Segmentation by Utilizing the Pleasure-Arousal-Dominance Information

Cited by 48 publications

References 32 publications

COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization

COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization

Recognizing induced emotions of movie audiences: Are induced and perceived emotions the same?

A Large Video Database for Computational Models of Induced Emotion

Contact Info

Product

Resources

About