An Effective News Anchorperson Shot Detection Method Based on Adaptive Audio/Visual Model Generation

Kim, Sang-Kyun; Hwang, Doo Sun; Kim, Ji-Yeun; Seo, Yang-Seock

doi:10.1007/11526346_31

Cited by 8 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An anchorperson shot is usually a starting point of a news story unit [6], [16], [17]. Faces of anchorpersons are key information for finding them in news videos.…”

Section: News Anchorperson Shot Detectionmentioning

confidence: 99%

“…Extraction of semantic information has shown promise for sports and news contents. For example, there have been studies on the detection of important events from sports programs [1], [2] and the generation of a navigation map of scene units by detecting article boundaries in news programs [3]- [6]. The main goal of these studies has been to minimize the gap between video semantic information sought by users and information from the low-level features extracted from videos.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Personal Videocasting System with Intelligent TV Browsing for a Practical Video Application Environment

Kim¹,

Jeong²,

Kim³

et al. 2009

ETRI Journal

Self Cite

View full text Add to dashboard Cite

In this paper, a video broadcasting system between a home-server-type device and a mobile device is proposed. The home-server-type device can automatically extract semantic information from video contents, such as news, a soccer match, and a baseball game. The indexing results are utilized to convert the original video contents to a digested or arranged format. From the mobile device, a user can make recording requests to the home-server-type devices and can then watch and navigate recorded video contents in a digested form. The novelty of this study is the actual implementation of the proposed system by combining the actual IT environment that is available with indexing algorithms. The implementation of the system is demonstrated along with experimental results of the automatic video indexing algorithms. The overall performance of the developed system is compared with existing state-of-the-art personal video recording products.

show abstract

“…An anchorperson shot is usually a starting point of a news story unit [6], [16], [17]. Faces of anchorpersons are key information for finding them in news videos.…”

Section: News Anchorperson Shot Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Personal Videocasting System with Intelligent TV Browsing for a Practical Video Application Environment

Kim¹,

Jeong²,

Kim³

et al. 2009

ETRI Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sound energy investigation is simple to implement and has been widely used in literature (e.g. [16]). However, even if sound loudness and sound energy are two different metrics, for the purpose of this paper it is safe to consider audio energy as a measure of sound loudness.…”

Section: B Analysis Of the Audio Energymentioning

confidence: 99%

“…Fast Play dynamically adapts the threshold for the audio level noticeable by humans using the approach proposed in [16], whereas the threshold to identify sudden increase/decrease of the audio energy is set to a 20% difference in the average audio energy between two consecutive frames. Both thresholds have been proven to be effective through experiments.…”

Section: B Analysis Of the Audio Energymentioning

confidence: 99%

“…The analyzed videos are DiVX encoded at 25 frames per second, with one audio channel (44.100 audio samples per second), and with a video resolution that ranges from 640x340 (movies) to 352x288 (all the other videos). Note that, to simplify the audio energy computation, Fast Play computes audio energy considering one audio sample out of ten, as described in [16]. Table I shows results obtained by applying the different proposed heuristics to videos with different characteristics.…”

Section: Experimental Assessmentmentioning

confidence: 99%

See 1 more Smart Citation