Semantic Enhanced(语义增强)研究综述
Semantic Enhanced 语义增强 - In this paper, we present a local semantic enhanced ConvNet (LSE-Net) for aerial scene recognition, which mimics the human visual perception of key local regions in aerial scenes, in the hope of building a discriminative local semantic representation. [1] The second is instance-based similarity matching using the Semantically enhanced Nearest Neighbour method (SeNN), which is employed in order to compare and quantify the semantic enhanced nearest neighbour entities/labels to predict the exact similarities. [2] Toward this end, we present a novel hierarchical semantic enhanced directional graph network. [3] To develop an effective e-Commerce recommender system that addresses these limitations, we propose a Trust-Semantic enhanced Multi-Criteria CF (TSeMCCF) approach that exploits the trust relations and multi-criteria ratings of users, and the semantic relations of items within the CF framework to achieve effective results when sufficient rating data are not available. [4] This paper proposes a semantic enhanced encoder-decoder network to tackle this problem. [5] A Semantic Enhanced Network called SeENet is constructed with the parallel pyramid to implement precise segmentation. [6]在本文中,我们提出了一种用于航空场景识别的局部语义增强卷积网络(LSE-Net),它模仿人类对航空场景中关键局部区域的视觉感知,以期构建具有判别性的局部语义表示。 [1] 第二个是使用语义增强最近邻方法(SeNN)的基于实例的相似性匹配,该方法用于比较和量化语义增强的最近邻实体/标签以预测确切的相似性。 [2] 为此,我们提出了一种新颖的分层语义增强有向图网络。 [3] 为了开发一个有效的电子商务推荐系统来解决这些限制,我们提出了一种信任语义增强的多标准 CF (TSeMCCF) 方法,该方法利用了用户的信任关系和多标准评级,以及项目内的语义关系。当没有足够的评级数据可用时,CF 框架可实现有效结果。 [4] 本文提出了一种语义增强的编码器-解码器网络来解决这个问题。 [5] 使用并行金字塔构建了一个名为 SeENet 的语义增强网络,以实现精确分割。 [6]