从视频到语义：基于知识图谱的视频语义分析技术
From Video to Semantic: Video Semantic Analysis Technology Based on Knowledge Graph
DOI: 10.12677/CSA.2019.98178, PDF,   
作者: 邓莉琼*, 吴吉祥, 张 丽：空军通信士官学校，辽宁 大连
关键词: 知识图谱；视频；分类；语义分析；Knowledge Graph； Video； Classify； Semantic Analysis
摘要: 随着大规模视频的迅猛发展，视频理解受到了广泛的关注，为了填补视频特征与视频理解之间的语义鸿沟，本文提出了一种基于知识图谱的视频语义分析流程，采用了随机漫步方法对视频语义标签信息进行共生性概率的量化，研究了基于知识图谱的视频语义推理技术，相关的实验结果证明了知识图谱方法能有效提高视频语义分析的准确度，构建后的多层次视频语义模型支持在视频分类、视频标注及视频摘要等方面的应用，对媒体语义中的信息组织和知识管理有一定的指导意义。
Abstract: Video understanding has attracted much research attention especially since the recent availability of large-scale video benchmarks. In order to fill up the semantic gap between video features and understanding, this paper puts forward a video semantic analysis process based on knowledge graph, and adopts random walk to quantify semantic consistency between semantic labels. Then video semantic reasoning based-on knowledge graph is studied. The experimental results prove that knowledge graph can improve semantic understanding effectively. Finally, a constructed multilevel video semantic model supports applications in video classifying, video labeling and video ab-stract, which has some guiding significance for information organization and knowledge management of media semantic.
文章引用：邓莉琼, 吴吉祥, 张丽. 从视频到语义：基于知识图谱的视频语义分析技术[J]. 计算机科学与应用, 2019, 9(8): 1584-1590. https://doi.org/10.12677/CSA.2019.98178

参考文献

[1] Abu-El-Haija, S., Kothari, N., et al. (2016) Youtube-8M: A Large-Scale Video Classification Benchmark. Computer Science, arXiv preprint arXiv 2016:1609.08675.
[2] Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., et al. (2015) Beyond Short Snippets: Deep Networks for Video Classification. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, 7-12 June 2015, 4694-4702. [Google Scholar] [CrossRef] 
[3] Jordan, M.I. and Jacobs, R.A. (1994) Hierarchical Mixtures of Experts and the EM Algorithm. Neural Computation, 6, 181-214. [Google Scholar] [CrossRef] 
[4] Wang, Z., Kuan, K. Ravaut, M., et al. (2017) Truly Multi-Modal Youtube-8M Video Classification with Video, Audio, and Text. Computer Science, arxiv preprint arxiv 2017:1706.05461.
[5] 曹倩, 赵一鸣. 知识图谱的技术实现流程及相关应用[J]. 情报理论与实践, 2015, 38(12): 13-18.
[6] 邓莉琼, 张贵新, 郝向宁. 基于知识图谱的图像语义分析技术及应用研究[J]. 计算机科学与应用, 2018, 8(9): 1364-1371.
[7] Fang, Y., Kuan, K., Lin, J., Tan, C. and Chandrasekhar, V. (2017) Object Detection Meets Knowledge Graphs. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia, 19-25 August 2017, 1661-1667.
[8] 李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9): 2508-2515.
[9] Wang, H., Klaser, A., Schmid, C. and Liu, C.-L. (2011) Action Recognition by Dense Trajectories. 2011 IEEE Conference on Com-puter Vision and Pattern Recognition, Providence, RI, 20-25 June 2011, 3169-3176. [Google Scholar] [CrossRef] 
[10] Paulheim, H. (2017) Knowledge Graph Refinement: A Survey of Ap-proaches and Evaluation Methods. Semantic Web, 8, 489-508. [Google Scholar] [CrossRef] 
[11] Tong, H., Fa-loutsos, C. and Pan, J. (2006) Fast Random Walk with Restart and Its Applications. Sixth International Conference on Data Mining, Hong Kong, 18-22 December 2006, 613-622. [Google Scholar] [CrossRef] 
[12] 孙霞, 董乐红. 基于监督学习的同义关系自动抽取方法[J]. 西北大学学报, 2008, 38(1): 35-39.
[13] 李跃鹏, 金翠, 及俊川. 基于Word2vec的关键词提取算法[J]. 科研信息化技术与应用, 2015, 6(4): 54-59.
[14] 杨思洛, 韩瑞珍. 知识图谱研究现状及趋势的可视化分析[J]. 情报资料工作, 2012, 33(4): 22-28.