-
公开(公告)号：US20230069197A1
公开(公告)日：2023-03-02
申请号：US17983208
申请日：2022-11-08
Inventor： Wenhao WU , Yuxiang Zhao
Abstract: A method and an apparatus for training a video recognition model are provided. The method may include: dividing a sample video into a plurality of sample video segments; sampling a part of sample video frames from a sample video segment; inputting the part of sample video frames into a feature extraction network to obtain feature information of the sample video segment; performing convolution fusion on the feature information by using a dynamic segment fusion module to obtain fusion feature information, where a convolution kernel of the dynamic segment fusion module varies with different video inputs; inputting the fusion feature information to a fully connected layer to obtain an estimated category of the sample video; and performing a parameter adjustment based on a difference between the tag of a true category and the estimated category to obtain the video recognition model.
-
公开(公告)号：US20230036864A1
公开(公告)日：2023-02-02
申请号：US17963058
申请日：2022-10-10
Inventor： Wenhao WU , Yuxiang Zhao
IPC: G06V20/54 , G08G1/052 , G08G1/056 , G08G1/16 , G06V10/762
Abstract: The present disclosure provides a method and apparatus for detecting a traffic anomaly, relates to the field of artificial intelligence and specifically to computer vision and deep learning technologies, and can be applied to video analysis scenarios. A specific implementation comprises: acquiring at least two frames of consecutive traffic images; identifying respectively a position of a target vehicle from the at least two frames of consecutive traffic images to obtain a position information set; determining a direction of travel and speed of the target vehicle according to the position information set; and comparing the direction of travel and speed of the target vehicle with a pre-generated vehicle vector field to determine whether the target vehicle is abnormal.
-
公开(公告)号：US20230004589A1
公开(公告)日：2023-01-05
申请号：US17577561
申请日：2022-01-18
Inventor： Wenhao WU , Wei LI , Xinyan XIAO , Jiachen LIU
Abstract: The present disclosure provides a summary generation model training method and apparatus, a device and a storage medium, and relates to the field of computer technologies, and in particular, to the field of artificial intelligence such as natural language processing and deep learning. The summary generation model training method includes: acquiring a document representation corresponding to a document sample; constructing, based on the document representation, a summary representation corresponding to the document representation, the summary representation including a positive summary representation and a negative summary representation; and constructing a total contrastive loss function based on the document representation, the positive summary representation and the negative summary representation, and training a summary generation model based on the total contrastive loss function. The present disclosure may improve accuracy of the summary generation model.
-
-
Search Results
3
records
(took 0.016 seconds)
