Weakly-supervised temporal attention 3D network for human action recognition

作者：

Highlights：

• We propose weakly-supervised temporal attention 3D network for human action recognition, called TA3DNet.

• TA3DNet consists of two subnetworks: temporal frame selection and weakly supervised temporal attention.

• We accelerate 3D convolutional neural networks (3D CNNs) by temporally assigning different importance to each frame

• We adopt weakly-supervised learning to successfully train an action recognition model from given labels.

摘要

•We propose weakly-supervised temporal attention 3D network for human action recognition, called TA3DNet.•TA3DNet consists of two subnetworks: temporal frame selection and weakly supervised temporal attention.•We accelerate 3D convolutional neural networks (3D CNNs) by temporally assigning different importance to each frame•We adopt weakly-supervised learning to successfully train an action recognition model from given labels.

论文关键词：Action recognition,Temporal attention,Convolutional neural network,Weakly-supervised learning,Video analysis,Video classification

论文评审过程：Received 24 February 2020, Revised 12 April 2021, Accepted 16 May 2021, Available online 27 May 2021, Version of Record 11 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108068