Publication
3D CNNs on distance matrices for human action recognition
Conference Article
Conference
ACM Conference on Multimedia (MM)
Edition
25th
Pages
1087-1095
Doc link
https://doi.org/10.1145/3123266.3123299
File
Authors
-
Hernández Ruiz, Alejandro José
-
Porzi, Lorenzo
-
Rota Bulò, Samuel
-
Moreno Noguer, Francesc
Projects associated
Abstract
In this paper we are interested in recognizing human actions from sequences of 3D skeleton data. For this purpose we combine a 3D Convolutional Neural Network with body representations based on Euclidean Distance Matrices (EDMs), which have been recently shown to be very effective to capture the geometric structure of the human pose. One inherent limitation of the EDMs, however, is that they are defined up to a permutation of the skeleton joints, i.e., randomly shuffling the ordering of the joints yields many different representations. In oder to address this issue we introduce a novel architecture that simultaneously, and in an end-to-end manner, learns an optimal transformation of the joints, while optimizing the rest of parameters of the convolutional network. The proposed approach achieves state-of-the-art results on 3 benchmarks, including the recent NTU RGB-D dataset, for which we improve on previous LSTM-based methods by more than 10 percentage points, also surpassing other CNN-based methods while using almost 1000 times fewer parameters.
Categories
pattern recognition.
Author keywords
3d convolutional neural networks, activity recognition, deep learning, human action recognition
Scientific reference
A. Hernandez Ruiz, L. Porzi, S. Rota and F. Moreno-Noguer. 3D CNNs on distance matrices for human action recognition, 25th ACM Conference on Multimedia, 2017, Mountain View, CA. USA., pp. 1087-1095.
Follow us!