Loading...
Please wait, while we are loading the content...
Affective ranking of movie scenes using physiological signals and content analysis
| Content Provider | ACM Digital Library |
|---|---|
| Author | Kierkels, Joep J.M. Soleymani, Mohammad Pun, Thierry Chanel, Guillaume |
| Abstract | In this paper, we propose an approach for affective ranking of movie scenes based on the emotions that are actually felt by spectators. Such a ranking can be used for characterizing the affective, or emotional, content of video clips. The ranking can for instance help determine which video clip from a database elicits, for a given user, the most joy. This in turn will permit video indexing and retrieval based on affective criteria corresponding to a personalized user affective profile. A dataset of 64 different scenes from 8 movies was shown to eight participants. While watching, their physiological responses were recorded; namely, five peripheral physiological signals (GSR - galvanic skin resistance, EMG - electromyograms, blood pressure, respiration pattern, skin temperature) were acquired. After watching each scene, the participants were asked to self-assess their felt arousal and valence for that scene. In addition, movie scenes were analyzed in order to characterize each with various audio- and video-based features capturing the key elements of the events occurring within that scene. Arousal and valence levels were estimated by a linear combination of features from physiological signals, as well as by a linear combination of content-based audio and video features. We show that a correlation exists between arousal- and valence-based rankings provided by the spectator's self-assessments, and rankings obtained automatically from either physiological signals or audio-video features. This demonstrates the ability of using physiological responses of participants to characterize video scenes and to rank them according to their emotional content. This further shows that audio-visual features, either individually or combined, can fairly reliably be used to predict the spectator's felt emotion for a given scene. The results also confirm that participants exhibit different affective responses to movie scenes, which emphasizes the need for the emotional profiles to be user-dependant. |
| Starting Page | 32 |
| Ending Page | 39 |
| Page Count | 8 |
| File Format | |
| ISBN | 9781605583167 |
| DOI | 10.1145/1460676.1460684 |
| Language | English |
| Publisher | Association for Computing Machinery (ACM) |
| Publisher Date | 2008-10-31 |
| Publisher Place | New York |
| Access Restriction | Subscribed |
| Subject Keyword | Affective computing Multimedia indexing and retrieval Physiological signals Affective personalization and ranking Emotion recognition and assessment |
| Content Type | Text |
| Resource Type | Article |
