公开(公告)号：US11715258B2

公开(公告)日：2023-08-01

申请号：US17243594

申请日：2021-04-29

Applicant: University of Electronic Science and Technology of China

Inventor： Ping Kuang ,  Liang Peng ,  Xiaofeng Gu

IPC: G06T17/00 ,  G06T15/20 ,  G06N3/04 ,  G06N3/08 ,  G06V10/82 ,  G06F18/213 ,  G06F18/21 ,  G06V10/764 ,  G06V10/84 ,  G06V20/64

CPC classification number: G06T17/00 ,  G06F18/213 ,  G06F18/217 ,  G06N3/04 ,  G06N3/08 ,  G06T15/205 ,  G06V10/764 ,  G06V10/82 ,  G06V10/84 ,  G06V20/64 ,  G06T2210/22

Abstract: The present invention provides a method for reconstructing a 3D object based on dynamic graph network, first, obtaining a plurality of feature vectors from 2D image I of an object; then, preparing input data: predefining an initial ellipsoid mesh, obtaining a feature input X by filling initial features and creating a relationship matrix A corresponding to the feature input X; then, inputting the feature input X and corresponding relationship matrix A to a dynamic graph network for integrating and deducing of each vertex's feature, thus new relationship matrix is obtained and used for the later graph convoluting, which improves the initial graph information and makes the initial graph information adapted to the mesh relation of the corresponding object, therefore the accuracy and the effect of 3D object reconstruction have been improved; last, regressing the position, thus the 3D structure of the object is deduced, and the 3D object reconstruction is completed.

公开(公告)号：US11620449B2

公开(公告)日：2023-04-04

申请号：US17024726

申请日：2020-09-18

Applicant: University of Electronic Science and Technology of China

Inventor： Jianping Li ,  Xiaofeng Gu ,  Jian Hu ,  Ruinan Sun ,  Wenting Feng ,  Shunli Li ,  Sheng Jiang

IPC: G06F40/30 ,  G06N20/00 ,  G06F40/289 ,  G06F40/216 ,  G06F17/16 ,  G06K9/62

Abstract: A method for machine reading comprehension includes: S1, obtaining a character-level indication vector of a question and a character-level indication vector of an article; S2, obtaining an encoded question vector and an encoded article vector; S3, obtaining an output P1 of a bidirectional attention model and an output P2 of a shared attention model; S4, obtaining an aggregated vector P3; S5, obtaining a text encoding vector P4; S6, obtaining global interaction information between words within the article; S7, obtaining a text vector P5 after using the self-attention model; S8, obtaining aggregated data P6 according to the text encoding vector P4 and the text vector P5; S9, obtaining a context vector of the article according to the aggregated data P6 and an unencoded article vector P; and S10, predicting an answer position according to the context vector of the article and the encoded question vector to complete the machine reading comprehension.