no code implementations • CVPR 2023 • Ryo Hachiuma, Fumiaki Sato, Taiki Sekii
A point cloud deep-learning paradigm is introduced to the action recognition, and a unified framework along with a novel deep neural network architecture called Structured Keypoint Pooling is proposed.
Ranked #1 on Skeleton Based Action Recognition on HMDB51
no code implementations • CVPR 2023 • Fumiaki Sato, Ryo Hachiuma, Taiki Sekii
Particularly, during the training phase using normal samples, the method models the distribution of skeleton features of the normal actions while freezing the weights of the DNNs and estimates the anomaly score using this distribution in the inference phase.
no code implementations • ECCV 2018 • Taiki Sekii
We propose a novel method to detect an unknown number of articulated 2D poses in real time.
no code implementations • CVPR 2016 • Taiki Sekii
A major limitation of previous techniques is foreground confusion, in which the shapes of objects and/or ghosting artifacts are ignored and are hence not appropriately specified in foreground regions.