Multiple Granularity Group Interaction Prediction

Taiping Yao, Minsi Wang, Bingbing Ni, Huawei Wei, Xiaokang Yang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 2246-2254

Abstract


Most human activity analysis works (i.e., recognition or prediction) only focus on a single granularity, i.e., either modelling global motion based on the coarse level movement such as human trajectories or forecasting future detailed action based on body parts’ movement such as skeleton motion. In contrast, in this work, we propose a multi-granularity interaction prediction network which integrates both global motion and detailed local action. Built on a bi- directional LSTM network, the proposed method possesses between granularities links which encourage feature sharing as well as cross-feature consistency between both global and local granularity (e.g., trajectory or local action), and in turn predict long-term global location and local dynamics of each individual. We validate our method on several public datasets with promising performance.

Related Material


[pdf]
[bibtex]
@InProceedings{Yao_2018_CVPR,
author = {Yao, Taiping and Wang, Minsi and Ni, Bingbing and Wei, Huawei and Yang, Xiaokang},
title = {Multiple Granularity Group Interaction Prediction},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}