Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation

doi:10.1016/j.patcog.2016.09.046

	Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation
	Wang, Yuhang1,2 ; Liu, Jing1 ; Li, Yong1,2 ; Fu, Jun1,2 ; Xu, Min 3; Lu, Hanqing1 ; Jing Liu
发表期刊	PATTERN RECOGNITION
	2017-04-01
卷号	64 期号:1 页码:437-445
文章类型	Article
摘要	Semantic video segmentation is a challenging task of fine-grained semantic understanding of video data. In this paper, we present a jointly trained deep learning framework to make the best use of spatial and temporal information for semantic video segmentation. Along the spatial dimension, a hierarchically supervised deconvolutional neural network (HDCNN) is proposed to conduct pixel-wise semantic interpretation for single video frames. HDCNN is constructed with convolutional layers in VGG-net and their mirrored deconvolutional structure, where all fully connected layers are removed. And hierarchical classification layers are added to multi scale deconvolutional features to introduce more contextual information for pixel-wise semantic interpretation. Besides, a coarse-to-fine training strategy is adopted to enhance the performance of foreground object segmentation in videos. Along the temporal dimension, we introduce Transition Layers upon the structure of HDCNN to make the pixel-wise label prediction consist with adjacent, pixels across space and time domains. The learning process of the Transition Layers can be implemented as a set of extra convolutional calculations connected with HDCNN. These two parts are jointly trained as a unified deep network in our approach. Thorough evaluations are performed on two challenging video datasets, i.e., CamVid and GATECH. Our approach achieves state-of-the-art performance on both of the two datasets.
关键词	Semantic Video Segmentation Deconvolutional Neural Network Coarse-to-fine Training Spatio-temporal Consistence
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.patcog.2016.09.046
关键词[WOS]	DATABASE
收录类别	SCI
语种	英语
项目资助者	863 Program(2014AA015104) ; National Natural Science Foundation of China(61332016 ; 61272329 ; 61472422)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000392682400036
引用统计	被引频次：30[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13435
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Jing Liu
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Univ Technol, Sydney, NSW, Australia
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Yuhang,Liu, Jing,Li, Yong,et al. Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation[J]. PATTERN RECOGNITION,2017,64(1):437-445.
APA	Wang, Yuhang.,Liu, Jing.,Li, Yong.,Fu, Jun.,Xu, Min.,...&Jing Liu.(2017).Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation.PATTERN RECOGNITION,64(1),437-445.
MLA	Wang, Yuhang,et al."Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation".PATTERN RECOGNITION 64.1(2017):437-445.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Hierarchically Super（1470KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载