Video annotation based on temporally consistent Gaussian random field

被引：9
|
作者：
Tang, J. [1 ]
Hua, X.-S.
Mei, T.
Qi, G.-J.
Wu, X.
机构：
[1] Univ Sci & Technol China, Dept Elect Engn & Informat Sci, Hefei 230027, Peoples R China
[2] Microsoft Res Asia, Beijing 100080, Peoples R China
[3] Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China
来源：
ELECTRONICS LETTERS | 2007年 / 43卷 / 08期
关键词：
D O I：
10.1049/el:20073674
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
A novel method for automatically annotating video semantics, called temporally consistent Gaussian random field (TCGRF) is proposed. Since the temporally adjacent video segments (e.g. shots) usually have a similar semantic concept, TCGRF adapts the temporal consistency property of video data into graph-based semi-supervised learning to improve the annotation results. Experiments conducted on the TREC-VID data set have demonstrated its effectiveness.
引用
下载
收藏
页码：448 / 449
页数：2
相关论文
共 50 条
  • [1] Temporally consistent gaussian random field for video semantic analysis
    Tang, Jinhui
    Hua, Xian-Sheng
    Mei, Tao
    Qi, Guo-Jun
    Li, Shipeng
    Wu, Xiuqing
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 2221 - +
  • [2] TEMPORALLY CONSISTENT VIDEO MATTING BASED ON BILAYER SEGMENTATION
    Tang, Zhen
    Miao, Zhenjiang
    Wan, Yanli
    2010 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME 2010), 2010, : 370 - 375
  • [3] TEMPORALLY CONSISTENT REGION-BASED VIDEO EXPOSURE CORRECTION
    Dong, Xuan
    Yuan, Lu
    Li, Weixin
    Yuille, Alan L.
    2015 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME), 2015,
  • [4] Temporally Consistent Semantic Video Editing
    Xu, Yiran
    AlBahar, Badour
    Huang, Jia-Bin
    COMPUTER VISION - ECCV 2022, PT XV, 2022, 13675 : 357 - 374
  • [5] Complete and temporally consistent video outpainting
    Dehan, Loic
    Van Ranst, Wiebe
    Vandewalle, Patrick
    Goedeme, Toon
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 686 - 694
  • [6] Region-based Temporally Consistent Video Post-processing
    Dong, Xuan
    Bonev, Boyan
    Zhu, Yu
    Yuille, Alan L.
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 714 - 722
  • [7] A motional but temporally consistent physical video examples
    Du, Zhenyu
    Wei, Xingxing
    Zhang, Weiming
    Liu, Fangzheng
    Bian, Huanyu
    Liu, Jiayang
    JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2022, 69
  • [8] TempFormer: Temporally Consistent Transformer for Video Denoising
    Song, Mingyang
    Zhang, Yang
    Aydin, Tunc O.
    COMPUTER VISION, ECCV 2022, PT XIX, 2022, 13679 : 481 - 496
  • [9] A motional but temporally consistent physical video examples
    Du, Zhenyu
    Wei, Xingxing
    Zhang, Weiming
    Liu, Fangzheng
    Bian, Huanyu
    Liu, Jiayang
    Journal of Information Security and Applications, 2022, 69
  • [10] Efficient Video Object Segmentation Based on Gaussian Mixture Model and Markov Random Field
    Liu, Zhi
    Gu, Jiandong
    Shen, Liquan
    Zhang, Zhaoyang
    ICSP: 2008 9TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-5, PROCEEDINGS, 2008, : 1006 - 1009
12345