Order-constrained representation learning for instructional video prediction
In this paper, we propose a weakly-supervised approach called Order-Constrained
Representation Learning (OCRL) to predict future actions from instructional videos by …
Representation Learning (OCRL) to predict future actions from instructional videos by …
An end-to-end multi-scale network for action prediction in videos
X Liu, J Yin, Y Sun, Z Zhang, J Tang - arXiv preprint arXiv:2301.01216, 2022 - arxiv.org
In this paper, we develop an efficient multi-scale network to predict action classes in partial
videos in an end-to-end manner. Unlike most existing methods with offline feature …
videos in an end-to-end manner. Unlike most existing methods with offline feature …
A Graph Convolutional Network with Early Attention Module for Skeleton-based Action Prediction
C Liu, X Zhao, Z Yan, Y Jiang… - 2022 26th International …, 2022 - ieeexplore.ieee.org
This paper addresses the problem of skeleton-based action prediction, which aims to predict
the action label when the skeleton sequence is partially observed. The action prediction task …
the action label when the skeleton sequence is partially observed. The action prediction task …