期刊文献+

媒介化公共外交的图像语义:基于Faster-RCNN技术的美国驻华使馆视频分析 被引量:1

The Image Semantics of Visual Public Diplomacy: A Faster-RCNN Analysis of the Official Videos Released by the U.S. Embassy in China
下载PDF
导出
摘要 本文使用计算机领域前沿的Faster-RCNN技术对美国驻华大使馆视频进行目标物视觉识别,并对数据进行统计检验和语义分析,挖掘美国外交视频向中国公众所传递的外交语义及意图。检验发现:检测目标"人"出现频数最高,是主导性关键视像且多以"单个人"形式出现;20类检测目标的出现频数存在显著差异,显示出信息发布意图的特殊性与指向性;引入统计学方法检测"人"出现次数的随机性,证明"人"的分布呈现规律性;将20类检测目标重新归类并统计检验,证明类别"人物"常与生活质量类别的物体关联出现。由此得出美国外交视频的图像语义:聚焦美国普通个体,渲染其民生幸福,以议程设置和框架构建维护美国霸权。 Using an image detection technique known as Faster-RCNN,this paper explores the image semantics conveyed through diplomatic videos by identifying objects on the official videos of the United States Embassy in China. The findings show that the object "person"which has the highest frequency is the dominant visual image,and it is repre sented in most cases in the form of"a single person."In addition,there is significant difference among the 20 categories of objects because of their different frequencies,indicating the uniqueness and directionality of the intentions of those who release the videos. Statistical methods that check the randomness of the "persons' "appearance frequency reveal that there is regular distribution of these "persons"who appear in the videos. What's more,after a re-classification of the 20 categories of objects,it is found that the category of "person"correlates with categories that denote the quality of life. This paper concludes that the image semantics conveyed by U. S. diplomatic videos indicates that the videos intend to promote US hegemony through agenda setting by focusing on average Americans and highlighting their happiness.
出处 《国际论坛》 CSSCI 北大核心 2018年第2期46-54,77-78,共9页 International Forum
基金 本文为国家社科基金项目“媒介化公共外交的机制与运用策略研究”(项目批准号:16BXW054)的阶段性成果.感谢清华大学计算机系刘华平副研究员提供技术支撑!
  • 相关文献

参考文献2

二级参考文献24

  • 1MarkoffJ. How many computers to identify a cat?[NJ The New York Times, 2012-06-25.
  • 2MarkoffJ. Scientists see promise in deep-learning programs[NJ. The New York Times, 2012-11-23.
  • 3李彦宏.2012百度年会主题报告:相信技术的力量[R].北京:百度,2013.
  • 410 Breakthrough Technologies 2013[N]. MIT Technology Review, 2013-04-23.
  • 5Rumelhart D, Hinton G, Williams R. Learning representations by back-propagating errors[J]. Nature. 1986, 323(6088): 533-536.
  • 6Hinton G, Salakhutdinov R. Reducing the dimensionality of data with neural networks[J]. Science. 2006, 313(504). Doi: 10. 1l26/science. 1127647.
  • 7Dahl G. Yu Dong, Deng u, et a1. Context-dependent pre?trained deep neural networks for large vocabulary speech recognition[J]. IEEE Trans on Audio, Speech, and Language Processing. 2012, 20 (1): 30-42.
  • 8Jaitly N. Nguyen P, Nguyen A, et a1. Application of pretrained deep neural networks to large vocabulary speech recognition[CJ //Proc of Interspeech , Grenoble, France: International Speech Communication Association, 2012.
  • 9LeCun y, Boser B, DenkerJ S. et a1. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, I: 541-551.
  • 10Large Scale Visual Recognition Challenge 2012 (ILSVRC2012)[OLJ.[2013-08-01J. http://www. image?net.org/challenges/LSVRC/2012/.

共引文献605

同被引文献19

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部