Temporal-Based Action Clustering for Motion Tendencies
Xingyu QIAN, Xiaogang Chen, Aximu Yuemaier, Shunfen Li, Weibang Dai, Zhitang Song · IEICE Transactions on Information and Systems · 2023
Video-based action recognition encompasses the recognition of appearance and the classification of action types. This work proposes a discrete-temporal-sequence-based motion tendency clustering framework to implement motion clustering by extracting motion tendencies and self-supervised learning. A published traffic intersection dataset (inD) and a self-produced gesture video set are used for evaluation and to validate the motion tendency action recognition hypothesis.