公开(公告)号：US11721130B2

公开(公告)日：2023-08-08

申请号：US17425653

申请日：2020-09-16

Applicant: Nanjing University of Science and Technology

Inventor： Yan Song ,  Rong Zou ,  Xiangbo Shu

IPC: G06V40/20 ,  G06V10/82 ,  G06V10/40

CPC classification number: G06V40/23 ,  G06V10/40 ,  G06V10/82

Abstract: The present disclosure relates to a weakly supervised video activity detection method and system based on iterative learning. The method includes: extracting spatial-temporal features of a video that contains actions; constructing a neural network model group; training a first neural network model according to the class label of the video, a class activation sequence output by the first neural network model, and a video feature output by the first neural network model; training the next neural network model according to the class label of the video, a pseudo temporal label output by the current neural network model, a class activation sequence output by the next neural network model, and a video feature output by the next neural network model; and performing action detection on the test video according to the neural network model corresponding to the highest detection accuracy value.

公开(公告)号：US20220189209A1

公开(公告)日：2022-06-16

申请号：US17425653

申请日：2020-09-16

Applicant: Nanjing University of Science and Technology

Inventor： Yan Song ,  Rong Zou ,  Xiangbo Shu

IPC: G06V40/20 ,  G06V10/82 ,  G06V10/40

Abstract: The present disclosure relates to a weakly supervised video activity detection method and system based on iterative learning. The method includes: extracting spatial-temporal features of a video that contains actions; constructing a neural network model group; training a first neural network model according to the class label of the video, a class activation sequence output by the first neural network model, and a video feature output by the first neural network model; training the next neural network model according to the class label of the video, a pseudo temporal label output by the current neural network model, a class activation sequence output by the next neural network model, and a video feature output by the next neural network model; and performing action detection on the test video according to the neural network model corresponding to the highest detection accuracy value.