-
公开(公告)号：US20210406579A1
公开(公告)日：2021-12-30
申请号：US17468848
申请日：2021-09-08
Inventor： Tianwei Lin , Dongliang He , Fu Li
Abstract: The present disclosure provides a model training method, an identification method, device, storage medium and program product, relating to computer vision technology and deep learning technology. In the solution provided by the present application, the image is deformed by the means of deforming the first training image without label itself, and the first unsupervised identification result is obtained by using the first model to identify the image before deformation, and the second unsupervised identification result is obtained by using the second model to identify the image after deformation, and the first unsupervised identification result of the first model is deformed, thus a consistency loss function can be constructed according to the second unsupervised identification result and the scrambled identification result. In this way, it is able to enhance the constraint effect of the consistency loss function and avoid destroying the scene semantic information of the images used for training.
-
公开(公告)号：US20230215132A1
公开(公告)日：2023-07-06
申请号：US18183439
申请日：2023-03-14
CPC classification number: G06V10/60 , G06T3/40 , G06T5/50 , G06V10/44 , G06V10/62 , G06V10/761 , G06T2207/20221
Abstract: A method for generating a relighted image includes: obtaining a to-be-processed image and a guidance image corresponding to the to-be-processed image; obtaining a first intermediate image consistent with an illumination condition in the guidance image by performing relighting rendering on the to-be-processed image in a time domain based on the guidance image; obtaining a second intermediate image consistent with the illumination condition in the guidance image by performing relighting rendering on the to-be-processed image in a frequency domain based on the guidance image; and obtaining a target relighted image corresponding to the to-be-processed image based on the first intermediate image and the second intermediate image.
-
公开(公告)号：US11430265B2
公开(公告)日：2022-08-30
申请号：US17022219
申请日：2020-09-16
Inventor： Zhizhen Chi , Fu Li , Hao Sun , Dongliang He , Xiang Long , Zhichao Zhou , Ping Wang , Shilei Wen , Errui Ding
Abstract: The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.
-
公开(公告)号：US20210192194A1
公开(公告)日：2021-06-24
申请号：US17022219
申请日：2020-09-16
Inventor： Zhizhen Chi , Fu Li , Hao Sun , Dongliang He , Xiang Long , Zhichao Zhou , Ping Wang , Shilei Wen , Errui Ding
Abstract: The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.
-
-
-
Search Results
4
records
(took 0.016 seconds)
