Abstract: A method of estimating an optical flow includes processing, using an image processing pass, a first image and a second image separately, and estimating the optical flow based on a second image attention feature map of the first image and a second image attention feature map of the second image. The processing using the image processing pass includes extracting a feature map by encoding an image, outputting a first image fusion attention feature map by fusing row relationship information of the image with the image feature map, outputting a first image attention feature map of the image based on the first image fusion attention feature map and the image feature map, outputting a second image fusion attention feature map by fusing column relationship information of the image with the first image attention feature map, and generating a second image attention feature map of the image based on the second image fusion attention feature map and the first image attention feature map.

Abstract: A package structure including a semiconductor die, a redistribution circuit structure and an electronic device is provided. The semiconductor die is laterally encapsulated by an insulating encapsulation. The redistribution circuit structure is disposed on the semiconductor die and the insulating encapsulation. The redistribution circuit structure includes a colored dielectric layer, inter-dielectric layers and redistribution conductive layers embedded in the inter-dielectric layers. The electronic device is disposed over the colored dielectric layer and electrically connected to the redistribution circuit structure.

Abstract: A manufacturing method of a SRAM memory device includes forming two transistors on a substrate, forming an inner dielectric layer covering the two transistors, forming contacts in the inner dielectric layer for coupling to source nodes of the two transistors, forming a metal interconnect structure on the inner dielectric layer, wherein a portion of an n-th metal layer of the metal interconnect structure is utilized as a lower metal layer, wherein n?1. An opening is formed in the metal interconnect structure to expose the lower metal layer, and then a capacitor is formed in the opening. The capacitor includes the lower metal layer, a first electrode layer, a dielectric layer, a second electrode layer, and an upper metal layer from bottom to top. The upper metal layer is a portion of an m-th metal layer of the metal interconnect structure, wherein m?n+1.

Abstract: An image compression method includes obtaining a hidden variable of an input image using a coding network of a deep learning neural network comprising at least one downsampling back projection module including performing downsampling transformation on a first feature map of the input image input to the downsampling back projection module to obtain a second feature map, obtaining a third feature map having a same resolution as a resolution of the first feature map by reconstructing the second feature map, and obtaining a fourth feature map as an optimization result of the second feature map, based on a difference value between the first feature map and the third feature map; and obtaining a bitstream file of a compressed image by performing entropy coding based on the hidden variable obtained based on the fourth feature map of a last downsampling back projection module.