Abstract: To better characterize the differences in category features in Facial Expression Recognition (FER) tasks, and improve inter-class separability and intra-class compactness, we propose a ...

Abstract: The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from ...

Abstract: Embedded artificial intelligence (AI) seamlessly integrates AI into everyday devices. By bringing AI closer to the data source, embedded AI empowers real-time decision making, enhanced ...

Abstract: Metasurfaces, ultrathin two-dimensional version of metamaterials, have attracted tremendous attention due to their exotic capabilities to freely manipulate electromagnetic waves. By ...

Abstract: Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive ...

Abstract: Existing image fusion methods always use hand-crafted fusion rules due to the uninterpretability of deep feature maps, which restrict the performance of networks and result in distortion. To ...