Junxing Ren

TL;DR: A method based on a 3D backbone network for multi scale spatial feature representation, which uses a pyramid pooling layer to allow the input of video frames at different scales, and then aggregates short-term spatial–temporal features into a long-term video-level representation is proposed.

TL;DR: The proposed architecture follows the two-stream network with a novel 3D Convolutional Network (ConvNets) and pyramid pooling layer, to design an end-to-end behavioral feature learning method that preserves the complete contextual relation of temporal human actions in videos.

TL;DR: In this paper, the authors proposed a skeleton transformer based on graph convolutional networks (GCsT), which employs all the benefits of Transformer (i.e. dynamical attention and global context) while keeping the advantages of GCNs.

TL;DR: Wang et al. as discussed by the authors proposed a robust action feature extractor, graph attention convolutional network with motion tempo enhancement (MTEA-GCN), which captures different joint motion tempos with two streams.