中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Hierarchically Supervised Deconvolutional Network for Semantic Video Segmentation

文献类型：期刊论文

作者Wang, Yuhang1,2; Liu, Jing1; Li, Yong1,2; Fu, Jun1,2; Xu, Min3; Lu, Hanqing1; Jing Liu
刊名PATTERN RECOGNITION
出版日期2017-04-01
卷号64期号:1页码:437-445
关键词Semantic Video Segmentation Deconvolutional Neural Network Coarse-to-fine Training Spatio-temporal Consistence
DOI10.1016/j.patcog.2016.09.046
文献子类Article
英文摘要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.
WOS关键词DATABASE
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000392682400036
资助机构863 Program(2014AA015104) ; National Natural Science Foundation of China(61332016 ; 61272329 ; 61472422)
源URL[http://ir.ia.ac.cn/handle/173211/13435]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
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
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。