With the development of artificial intelligence, more and people hope that computers can understand human language through natural technology, learn to think like beings, finally replace beings complete highly difficult tasks with cognitive ability. As key technology understanding, sentence representation reasoning mainly focuses on method model. Although performance has been improved, there ar...

Model generalization to the unseen scenes is crucial real-world applications, such as autonomous driving, which requires robust vision systems. To enhance model generalization, domain through learning domain-invariant representation has been widely studied. However, most existing works learn shared feature space within multi-source domains but ignore characteristic of itself (e.g., sensitivity ...

Abstract The amount of Internet data is increasing day by with the rapid development information technology. To process massive amounts and solve overload, researchers proposed recommender systems. Traditional recommendation methods are mainly based on collaborative filtering algorithms, which have sparsity problems. At present, most model-based algorithms can only capture first-order semantic ...

Spreading Activation Within Semantic Categories: Comments on. Roschs Cognitive Representations of Semantic Categories.concerning the role of prototypes in cognitive processing, representation, and. 1975c, for natural superordinate semantic categories Rosch, 1975b, and for.Her research interests include cognition, concepts, causality, thinking, memory, and. 1975, Cognitive representation of sema...

Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while implicit semantic associations behind highly complex interactions graphs largely unexploited. In this paper, we propose Semantic Graph Convolutional Networks (SGCN) that explores semantics latent semantic-paths graphs. previous wor...

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer performance compared to fully-supervised methods, seeming deliver message that human labels hardly contribute transferrable features. In this paper, we defend usefulness semantic but point out and metho...