Video Highlight Detection via Region-Based Deep Ranking Model

doi:10.1142/S0218001419400019

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多媒体计算与图形学团队

	Video Highlight Detection via Region-Based Deep Ranking Model
	Jiao, Yifan 1,2; Zhang, Tianzhu2 ; Huang, Shucheng 1; Liu, Bin 3; Xu, Changsheng2
刊名	INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
	2019-06-30
卷号	33 期号:7 页码:14
关键词	Video highlight detection position-sensitive fully convolutional network
ISSN号	0218-0014
DOI	10.1142/S0218001419400019
通讯作者	Huang, Shucheng(schuang2015@gmail.com)
英文摘要	The video highlight detection task is to localize key elements (moments of user's major or special interest) in a video. Most of the existing highlight detection approaches extract features from the video segment as a whole without considering the difference of local features spatially. In spatial extent, not all regions are worth watching because some of them only contain the background of the environment without human or other moving objects, especially when there is lots of clutter in the background. To deal with this issue, we propose a novel region-based model which can automatically localize the key elements in a video without any extra supervised annotations. Specifically, the proposed model produces position-sensitive score maps for local regions in the spatial dimension of the video segment, and then aggregates all position-wise scores with position-pooling operation. The regions with higher response values will be extracted as key elements. Thus more effective features of the video segment are obtained to predict the highlight score. The proposed position-sensitive scheme can be easily integrated into an endto-end fully convolutional network which aims to update parameters via stochastic gradient descent method in the backward propagation to improve the robustness of the model. Extensive experimental results on the YouTube and SumMe datasets demonstrate that the proposed approach achieves significant improvement over state-of-the-art methods.
资助项目	National Natural Science Foundation of China[61432019] ; National Natural Science Foundation of China[61572498] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[61772244] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; Beijing Natural Science Foundation[4172062] ; Postgraduate Research & Practice Innovation Program of Jiangsu Province[SJCX17 0599]
WOS关键词	SCENE DETECTION
WOS研究方向	Computer Science
语种	英语
出版者	WORLD SCIENTIFIC PUBL CO PTE LTD
WOS记录号	WOS:000470871900001
资助机构	National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; Beijing Natural Science Foundation ; Postgraduate Research & Practice Innovation Program of Jiangsu Province
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/26012]
专题	多媒体计算与图形学团队
通讯作者	Huang, Shucheng
作者单位	1.Jiangsu Univ Sci & Technol, Zhenjiang 212003, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Moshanghua Tech Co Ltd, Beijing 100030, Peoples R China
推荐引用方式 GB/T 7714	Jiao, Yifan,Zhang, Tianzhu,Huang, Shucheng,et al. Video Highlight Detection via Region-Based Deep Ranking Model[J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE,2019,33(7):14.
APA	Jiao, Yifan,Zhang, Tianzhu,Huang, Shucheng,Liu, Bin,&Xu, Changsheng.(2019).Video Highlight Detection via Region-Based Deep Ranking Model.INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE,33(7),14.
MLA	Jiao, Yifan,et al."Video Highlight Detection via Region-Based Deep Ranking Model".INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 33.7(2019):14.