Learning explicit video attributes from mid-level representation for video captioning

doi:10.1016/j.cviu.2017.06.012

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Learning explicit video attributes from mid-level representation for video captioning
	Nian, Fudong 1; Li, Teng 1,2; Wang, Yan 1; Wu, Xinyu 3; Ni, Bingbing 4; Xu, Changsheng2
刊名	COMPUTER VISION AND IMAGE UNDERSTANDING
	2017-10-01
卷号	163 页码:126-138
关键词	Mid-level Video Representation Video Attributes Learning Video Caption Sequence-to-sequence Learning
DOI	10.1016/j.cviu.2017.06.012
文献子类	Article
英文摘要	Recent works on video captioning mainly learn the map from low-level visual features to language description directly without explicitly representing the high-level semantic video concepts (e.g. objects, actions in the annotated sentences). To bridge the semantic gap, in this paper, addressing it, we propose a novel video attribute representation learning algorithm for video concept understanding and utilize the learned explicit video attribute representation to improve video captioning performance. To achieve it, firstly, inspired by the success of spectrogram in audio processing, a novel mid-level video representation named "video response map" (VRM) is proposed, by which the frame sequence could be represented by a single image representation. Therefore, the video attributes representation learning could be converted to a well-studied multi-label image classification problem. Then in the captions prediction step, the learned video attributes feature is integrated with the single frame feature to improve previous sequence-to sequence language generation model by adjusting the LSTM (Long-Short Term Memory) input units. The proposed video captioning framework could both handle variable frame inputs and utilize high-level semantic video attribute features. Experimental results on video captioning tasks show that the proposed method, utilizing only RGB frames as input without extra video or text training data, could achieve competitive performance with state-of-the-art methods. Furthermore, the extensive experimental evaluations on the UCF-101 action classification benchmark well demonstrate the representation capability of the proposed VRM. (C) 2017 Elsevier Inc. All rights reserved.
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000418726800011
资助机构	National Natural Science Foundation (NSF) of China(61572029) ; China Postdoctoral Science Foundation(156613 ; 2016T90148)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/20758]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位	1.Anhui Univ, Minist Educ, Key Lab Intelligent Comp & Signal Proc, Hefei, Anhui, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.Chinese Acad Sci, Shenzhen Inst Adv Technol, Beijing, Peoples R China 4.Shandong Jiaotong Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Nian, Fudong,Li, Teng,Wang, Yan,et al. Learning explicit video attributes from mid-level representation for video captioning[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2017,163:126-138.
APA	Nian, Fudong,Li, Teng,Wang, Yan,Wu, Xinyu,Ni, Bingbing,&Xu, Changsheng.(2017).Learning explicit video attributes from mid-level representation for video captioning.COMPUTER VISION AND IMAGE UNDERSTANDING,163,126-138.
MLA	Nian, Fudong,et al."Learning explicit video attributes from mid-level representation for video captioning".COMPUTER VISION AND IMAGE UNDERSTANDING 163(2017):126-138.