Jinhui Zhu — accepted AI-conference papers

2020

Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition

Yukun Su, Guosheng Lin, Jinhui Zhu, Qingyao Wu

ECCV 2020poster

This paper introduces a new method for recognizing violent behavior by learning contextual relationships between related people from human skeleton points. Unlike previous work, we first formulate 3D skeleton point clouds from human skeleton sequences extracted from videos and then perform interacti…

Cited by 95 Source ↗PDF ↗Scholar ↗

2018

Discrimination-aware Channel Pruning for Deep Neural Networks

Zhuangwei Zhuang, Mingkui Tan, Bohan Zhuang, Jing Liu, Yong Guo, Qingyao Wu +2

NeurIPS 2018poster

Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature maps and the compressed ones. Both strategies suffer from s…

Cited by 791 Source ↗PDF ↗code ↗Scholar ↗