视频局部高层语义特征描述的是图像帧中的物体。
在基于内容的图像检索基础上,提出了基于高层语义词和颜色词检索。
This paper presents a new image retrieval method based on high-level semantics word and color name.
图像语义的标注需要解决图像高层语义和底层特征间存在的语义鸿沟。
The semantic gap between image semantic and visual features will be solved in image annotation.
准确提取视频高层语义特征,有助于更好地进行基于内容的视频检索。
Extracting high level features from video accurately benefits the content-based video retrieval.
在基于内容的图像检索中,图像的内容包括图像的低层视觉特征和高层语义。
The contents of image include low level visual features and high level semantic in image retrieval based on content.
通过这种方法,我们能够准确地提取多媒体传感器网络中的音频高层语义信息。
With the neural network based approach, human knowledge and machine learning are effectively combined together in the semantic inference.
本文实验详细的阐述了自动获取高层语义信息的过程,实验最后给出了描述模型实现的结果。
The experiment demonstrates the process of acquire high-layer semantic information automatically, at last, it shows the result of description model implementation.
为了全面准确地获取视频高层语义信息,提出了一种基于仿生的视频语义分析两级多模式融合算法。
To extract video semantic concepts combing different modalities, a two level multimodal fusion method for video semantic concept analysis is proposed.
如何跨越图像底层特征和高层语义之间的语义鸿沟,使机器自动的实现图像语义标注更是研究的难点。
How to annotate the image semantic automatically in order to across semantic gap between the feature and the high-level semantic of the image is a difficult problem.
为了缩短介于低层视觉特征与高层语义特征之间的“语义鸿沟”距离,提出了急需解决的两大关键问题。
This paper presented two key problems to shorten "semantic gap" distance between low-level visual features and high-level semantic features.
但是现有的检索技术多是基于底层视觉特征的检索,与人们所能理解的高层语义概念相去甚远,这严重地影响检索的实际效果。
But most information retrieval techniques are based on low-level features, which are quite different from the semantic concepts in human thought, affecting the retrieval results inevitably.
本文通过对现有基于内容图像标引及检索技术的简要介绍,提出应在现有系统中增加图像的高层语义概念描述,以更接近于人的视觉效果。
This paper introduced the technology of content based image indexing and retrieval concisely. It propose to increase high level semantic describe of image to approach visual sense of human being.
在基于内容的图像检索系统中,图像低层特征和图像所表达高层概念之间的不一致性导致系统出现语义鸿沟问题。
In content-based image retrieval systems, the inconsistency between image low-level features and the concept of high-level expressed by images lead to system semantic gap problem.
宏观结构是篇章的高层次语义结构。
Macro structure is the higher level semantic structure of a text.
其中情感语义是最高层的语义。
语义表达的——“言”的最高层次是用咏歌来体现,可见语言的语义性表达并非绝对优于音乐。
Semantic expression's highest level, "word", is manifested by chanting song, so it's obvious that speech's semantics expression by no means absolutely surpasses music.
语义表达的——“言”的最高层次是用咏歌来体现,可见语言的语义性表达并非绝对优于音乐。
Semantic expression's highest level, "word", is manifested by chanting song, so it's obvious that speech's semantics expression by no means absolutely surpasses music.
应用推荐