Abstract: 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).

Abstract: 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).

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.