Logo image
Human interaction prediction using deep temporal features
Journal article   Peer reviewed

Human interaction prediction using deep temporal features

Q. Ke, M. Bennamoun, S. An, F. Boussaid and F. Sohel
Computer Vision – ECCV 2016 Workshops, Vol.9914, pp.403-414
2016
url
Link to Published Version *Subscription may be requiredView

Abstract

Interaction prediction has a wide range of applications such as robot controlling and prevention of dangerous events. In this paper, we introduce a new method to capture deep temporal information in videos for human interaction prediction. We propose to use flow coding images to represent the low-level motion information in videos and extract deep temporal features using a deep convolutional neural network architecture. We tested our method on the UT-Interaction dataset and the challenging TV human interaction dataset, and demonstrated the advantages of the proposed deep temporal features based on flow coding images. The proposed method, though using only the temporal information, outperforms the state of the art methods for human interaction prediction.

Details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#11 Sustainable Cities and Communities

Source: InCites

Metrics

Logo image