Logo detection is a technology that identifies logos in images and returns their locations. With logo technology, brands can check how often are displayed on social media platforms elsewhere online they appear. It has received lot of attention for its wide applications across different sectors, such as brand identity protection, product management, duration monitoring. Particularly, offer vario...

Features play an important role in various visual tasks, especially place recognition applied to perceptually changing environments. We address challenges due dynamic and confusable patterns by proposing a discriminative semantic feature selection network named DSFeat this study. With supervision of both information attention mechanism, the pixel-wise stability features can be estimated, which ...

A manufacturing feature can be defined simply as a geometric shape and its manufacturing information to create the shape. In a feature-based process planning system, feature library that consists of pre-defined manufacturing features and the manufacturing information to create the shape of the features, plays an important role in the extraction of manufacturing features with their proper manufa...

Land cover semantic segmentation is an important technique in land. It very practical land resource protection planning, geographical classification, surveying and mapping analysis. Deep learning shows excellent performance picture recent years, but there are few algorithms for cover. When dealing with tasks, traditional networks often have disadvantages such as low precision weak generalizatio...

The performances of semisupervised clustering for unlabeled data are often superior to those unsupervised learning, which indicates that semantic information attached clusters can significantly improve feature representation capability. In a graph convolutional network (GCN), each node contains about itself and its neighbors is beneficial common unique features among samples. Combining these fi...

Existing image semantic segmentation methods favor learning consistent representations by extracting long-range contextual features with the attention, multi-scale, or graph aggregation strategies. These usually treat misclassified and correctly classified pixels equally, hence misleading optimization process causing inconsistent intra-class pixel feature in embedding space during learning. In ...