@inproceedings{3dae47c26dce4f2e890e7285218c2f43,
title = "Human interaction prediction using deep temporal features",
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.",
keywords = "CNN, Interaction prediction, Temporal convolution",
author = "Qiuhong Ke and Mohammed Bennamoun and Senjian An and Farid Boussaid and Ferdous Sohel",
year = "2016",
doi = "10.1007/978-3-319-48881-3_28",
language = "English",
isbn = "9783319488806",
volume = "9914 LNCS",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag London Ltd.",
pages = "403--414",
editor = "Gang Hua and Herve Jegou",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
address = "Germany",
note = "14th European Conference on Computer Vision, ECCV 2016 ; Conference date: 08-10-2016 Through 16-10-2016",
}