Researchers from the University of Gothenburg and Chalmers University of Technology have developed a modular neural decoder ...

CADRE is a family of video autoencoders from Kyutai built for action-conditioned world models. A world model generates in the autoencoder’s latent space. So the autoencoder’s compression sets both ...

GCN, cross-modal attention and AdaIN reported improved dance-generation quality, music synchronization and style control on ...

A new spatio-temporal graph network models players and the ball as a dynamic graph, detecting key match events and tactical patterns with record accuracy and real-time speed.

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing ...

ABSTRACT: The nearly analytic discretization of the frequency-domain wave equation produces large-scale, sparse, and ill-conditioned linear system, which challenge conventional iterative solvers. To ...

Abstract: In recent years, deep learning-based hyperspectral unmixing (HU) techniques have garnered increasing attention and achieved significant progress. However, existing deep learning methods ...

Electroencephalogram (EEG)-based emotion recognition has emerged as a compelling direction in affective computing, driven by its ability to provide objective, neural-level insights into emotional ...

Abstract: 3D meshes are fundamental data representations for capturing complex geometric shapes in computer vision and graphics applications. While Convolutional Neural Networks (CNNs) have excelled ...