@inproceedings{2528ce1dc6a7462d8b4d7f2bc50ddf79,
title = "Skeleton boxes: Solving skeleton based action detection with a single deep convolutional neural network",
abstract = "Action recognition from well-segmented 3D skeleton video has been intensively studied. However, due to the difficulty in representing the 3D skeleton video and the lack of training data, action detection from streaming 3D skeleton video still lags far behind its recognition counterpart and image-based object detection. In this paper, we propose a novel approach for this problem, which leverages both effective skeleton video encoding and deep regression based object detection from images. Our framework consists of two parts: skeleton-based video image mapping, which encodes a skeleton video to a color image in a temporal preserving way, and an end-to-end trainable fast skeleton action detector (Skeleton Boxes) based on image detection. Experimental results on the latest and largest PKU-MMD benchmark dataset demonstrate that our method outperforms the state-of-the-art methods with a large margin. We believe our idea would inspire and benefit future research in this important area.",
keywords = "CNN, detection, end-to-end, skeleton",
author = "Bo Li and Yuchao Dai and Xuelian Cheng and Huahui Chen and Yi Lin and Mingyi He",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 ; Conference date: 10-07-2017 Through 14-07-2017",
year = "2017",
month = sep,
day = "5",
doi = "10.1109/ICMEW.2017.8026283",
language = "English",
series = "2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "613--616",
booktitle = "2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017",
address = "United States",
}