News video monologue shot detection based on multimodality information

doi:10.3778/j.issn.1002-8331.2009.25.053

Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (25): 173-175.DOI: 10.3778/j.issn.1002-8331.2009.25.053

• 图形、图像、模式识别 • Previous Articles Next Articles

News video monologue shot detection based on multimodality information

JI Zhong，SU Yu-ting，YANG Yi-zheng

School of Electronic and Information Engineering，Tianjin University，Tianjin 300072，China

Received:2008-05-27 Revised:2008-08-18 Online:2009-09-01 Published:2009-09-01
Contact: JI Zhong

基于多模态信息融合的新闻独白镜头检测

冀中，苏育挺，杨益铮

天津大学电子信息工程学院，天津 300072

通讯作者: 冀中

Abstract

Abstract: Monologue shots are informative and valuable in the application of news video retrieval and mining.Multimodality information，such as audio，visual，temporal and contextual features is employed to detect them.Commercial and other shots are first removed by rules，and then anchorperson shots are detected by clustering method.At last monologue and reporter shots are labeled.The experimental results achieve better performance without external knowledge.

Key words: monologue shot detection, news video, video retrieval, multimodality, conditional random fields

摘要： 新闻视频中的独白镜头具有较大的信息量，在视频检索和挖掘中具有较高的应用价值。提出了一种融合音频、视频、时域以及上下文信息等多模态特征进行独白场景检测的方法。首先利用规则移除广告和“其他”镜头，然后应用聚类的方法检测主持人镜头，最后应用条件随机场（CRFs）模型标记独白和记者镜头。该方法无需额外的信息，具有较好的普适性，实验取得了较好的性能。

关键词: 独白镜头检测, 新闻视频, 视频检索, 多模态, 条件随机场

CLC Number:

TP391

JI Zhong，SU Yu-ting，YANG Yi-zheng. News video monologue shot detection based on multimodality information[J]. Computer Engineering and Applications, 2009, 45(25): 173-175.

冀中，苏育挺，杨益铮. 基于多模态信息融合的新闻独白镜头检测[J]. 计算机工程与应用, 2009, 45(25): 173-175.

[1]	LU Lixia, ZOU Junzhong, GUO Yucheng, ZHANG Jian, WANG Bei. Prediction of Knee Injury Based on Multimodal Fusion [J]. Computer Engineering and Applications, 2021, 57(9): 225-232.
[2]	LI Bo, KANG Xiaodong, ZHANG Huali, WANG Yage, CHEN Yayuan, BAI Fang. Named Entity Recognition in Chinese Electronic Medical Records Using Transformer-CRF [J]. Computer Engineering and Applications, 2020, 56(5): 153-159.
[3]	MA Dongmei, HE Sansan, YANG Caifeng, YAN Chunman. Semantic Segmentation Based on Convolutional Neural Networks with Feature Fusion [J]. Computer Engineering and Applications, 2020, 56(10): 193-198.
[4]	XU Tongyang1，2, ZHANG Guobiao1. Video retrieval research visual analysis [J]. Computer Engineering and Applications, 2017, 53(22): 190-197.
[5]	WANG Zuxing, LV Zhao, GU Junzhong. Hybrid method for Chinese person name recognition [J]. Computer Engineering and Applications, 2015, 51(8): 211-217.
[6]	SHI Qingwei, GUO Pengliang. Conditional random fields topic model based on LDA model [J]. Computer Engineering and Applications, 2015, 51(7): 131-135.
[7]	HUANG Yanjiao, WU Qin, LIANG Jiuzhen. Boosted constrained conditional random fields for Web object information extraction [J]. Computer Engineering and Applications, 2015, 51(23): 143-148.
[8]	ZHANG Jianming, LIU Haiyan, SUN Shumin. Key frame extraction based on improved ant algorithm and agglomerative [J]. Computer Engineering and Applications, 2013, 49(3): 222-225.
[9]	GAN Ling, WANG Ziyu. Video retrieval using pyramid matching with sparse coding [J]. Computer Engineering and Applications, 2013, 49(21): 191-194.
[10]	CHEN Shiwen, WU Jiangxing, HUANG Wanwei. DDoS attack detection method based on conditional random field with feature set [J]. Computer Engineering and Applications, 2013, 49(17): 9-11.
[11]	ZHAI Sulan, ZHA Daoli. Video retrieval based on visual feature and structural spectral feature [J]. Computer Engineering and Applications, 2012, 48(32): 176-180.
[12]	YU Jiangde¹，WANG Xijie¹，FAN Xiaozhong². Comparing of importance of above-context versus below-context for Chinese word segmentation [J]. Computer Engineering and Applications, 2011, 47(4): 117-120.
[13]	LIU Zhulong，ZHAO Yuqian，LIU Binxu. Multimodality elastic image registration based on local affine model [J]. Computer Engineering and Applications, 2011, 47(36): 219-221.
[14]	YAN Lelin. Research on video affective content recognition based on unascertained clustering [J]. Computer Engineering and Applications, 2011, 47(30): 165-167.
[15]	WANG Feng，ZHANG Xueying，LI Bingnan. Research of chord recognition based on MPCP and CRFs [J]. Computer Engineering and Applications, 2011, 47(18): 198-200.

News video monologue shot detection based on multimodality information

基于多模态信息融合的新闻独白镜头检测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics