Beijing University of Technology

Beijing Research Institute of Chemical Industry, China Petroleum & Chemical Corporation

China Petroleum & Chemical Corporation

Dehui Kong

Shaofan Wang

Lichun Wang

Jinghua Li

Kai Xu

Qi Zhang

Shuang Shuang Li

Meng Xu

Shijun Zhang

Hua Yin

Jingbo Shao

Hongwei Shi

Peng Kang

Dali Gao

Yiqing Bai

Mu Dong

Baige Chou

Yongpeng Wu

Changjin Li

Qi Xin

Caixia Liu

Baocai Yin

Yueming Ren

Mingfu Lv

Tao Cai

Yigang Tan

Jinqi He

Meijie Li

Yun Lv

Xiaoyong Gao

Changhui Sun

Guang Li

A thermoplastic composite material has an inner layer material and at least one layer of outer layer material. The inner layer material is a core layer that contains fiber bundles, a first thermoplastic resin and a first auxiliary agent; and the at least one layer of outer layer material wraps the core layer and is a resin layer comprising a second thermoplastic resin and an optional second auxiliary agent. The fiber bundles extend continuously from one end of the core layer to the opposite end thereof. The inner layer-outer layer composite structure improves the processing performance of the thermoplastic composite material and the lubricity between fibers and resin matrixes during injection molding, and improves the fluidity of the fibers in a resin matrix melt.

Thermoplastic composite material, preparation method therefor and use thereof

Dictionary learning method and means for zero-shot recognition can establish the alignment between visual space and semantic space at category layer and image level, so as to realize high-precision zero-shot image recognition. The dictionary learning method includes the following steps: (1) training a cross domain dictionary of a category layer based on a cross domain dictionary learning method; (2) generating semantic attributes of an image based on the cross domain dictionary of the category layer learned in step (1); (3) training a cross domain dictionary of the image layer based on the image semantic attributes generated in step (2); (4) completing a recognition task of invisible category images based on the cross domain dictionary of the image layer learned in step (3).

Dictionary learning method and means for zero-shot recognition

3D reconstruction method based on deep learning includes the following steps: (1) The potential vector constrained in the input image is used to reconstruct the complete 3D shape of the target, and the mapping between the part and the complete 3D shape is learned, then the 3D reconstruction of a single depth image is realized. (2) Learn the intermediate feature representation between the 3D real object and the reconstructed object to obtain the target potential variables in step (1). (3) The voxel floating value predicted in step (1) is transformed into binary value by using the limit learning machine to complete high-precision reconstruction.

3D reconstruction method based on deep learning

The invention discloses a method for three-dimensional human pose estimation, which can realize the real-time and high-precision 3D human pose estimation without high configuration hardware support and precise human body model. In this method for three-dimensional human pose estimation, including the following steps: (1) establishing a three-dimensional human body model matching the object, which is a cloud point human body model of visible spherical distribution constraint. (2) Matching and optimizing between human body model for human body pose tracking and depth point cloud. (3) Recovering for pose tracking error based on dynamic database retrieval.

Method for three-dimensional human pose estimation

Growing community of inventors

Beijing, China

Dehui Kong