2008 IEEE International Conference on Acoustics, Speech and Signal Processing 2008
DOI: 10.1109/icassp.2008.4518084
|View full text |Cite
|
Sign up to set email alerts
|

Visual-aural attention modeling for talk show video highlight detection

Abstract: In this paper, we propose a visual-aural attention modeling based video content analysis approach, which can be used to automatically detect the highlights of the popular TV program-talk show video. First, the visual and aural affective features are extracted to represent and model the human attention of highlight. For efficiency consideration, the adopted affective features are kept as few as possible. Then, a specific fusion strategy called ordinaldecision is used to combine the visual, aural attention model… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2010
2010
2020
2020

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(2 citation statements)
references
References 9 publications
0
2
0
Order By: Relevance
“…Related efforts in recent years have assessed learners' emotions by using human physiological signals, such as heart rate variability (HRV) and EEG (Chen & Sun, 2012;Chen & Wang, 2011) and attention (Chen & Lin, 2014;Rebolledo-Mendez et al, 2009). Moreover, EEG signals have also been successfully applied in computer-based assessment (Wolpaw, McFarland, Neat & Forneris, 1991), brain-computer interface (Schalk, McFarland, Hinterberger, Birbaumer & Wolpaw, 2004;Wolpaw, Birbaumer, McFarland, Pfurtscheller & Vaughan, 2002), visual-aural attention modeling (Zheng et al, 2008), classification of human emotion (Murugappan, Nagarajan & Yaacob, 2010) and assessment of learning performance (Harmony et al, 2001). Of previous studies that developed AAS based on physiological signals, Hsu et al (2012) developed a reading concentration monitoring system to facilitate reading activity with e-books in order to allow instructors to more thoroughly understand students' reading concentration states.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Related efforts in recent years have assessed learners' emotions by using human physiological signals, such as heart rate variability (HRV) and EEG (Chen & Sun, 2012;Chen & Wang, 2011) and attention (Chen & Lin, 2014;Rebolledo-Mendez et al, 2009). Moreover, EEG signals have also been successfully applied in computer-based assessment (Wolpaw, McFarland, Neat & Forneris, 1991), brain-computer interface (Schalk, McFarland, Hinterberger, Birbaumer & Wolpaw, 2004;Wolpaw, Birbaumer, McFarland, Pfurtscheller & Vaughan, 2002), visual-aural attention modeling (Zheng et al, 2008), classification of human emotion (Murugappan, Nagarajan & Yaacob, 2010) and assessment of learning performance (Harmony et al, 2001). Of previous studies that developed AAS based on physiological signals, Hsu et al (2012) developed a reading concentration monitoring system to facilitate reading activity with e-books in order to allow instructors to more thoroughly understand students' reading concentration states.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Kayser proposed an audio attention computational model based on extracting contrast characters of intensity, duration and frequency from the Flourier spectrum in multi-scale to construct a bottom-up audio saliency map [5]. Zheng extracted audio features including short-term average energy, pitch, the average zero-crossing rate in his audio attention computational model to represent the strength of sounds, the sharpness of speeches and the degree of the urgency of audio [11]. Wang divided the audio signal into sub-frames to calculate the short-term energy, then, basing on the characteristics of auditory stream, energy spectrum of each channel was timedomain filtered in different scales through Gaussian filter groups and the auditory saliency map finally was achieved by linear combination of each frequency channel saliency [12].…”
Section: Related Workmentioning
confidence: 99%