Action Recognition With Spatio-Temporal Visual Attention on Skeleton Image Sequences

• Published in: IEEE transactions on circuits and systems for video technology Vol. 29; no. 8; pp. 2405 - 2415
• Main Authors: Yang, Zhengyuan, Li, Yuncheng, Yang, Jianchao, Luo, Jiebo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Action and activity recognition; Architecture; Artificial neural networks; Aspect ratio; Datasets; human analysis; Image enhancement; Image recognition; Image sequences; Joints (anatomy); Object recognition; Optical imaging; Performance enhancement; Representations; Semantics; Skeleton; Three-dimensional displays; Two dimensional displays; video understanding; visual attention; Visualization
• DOI: 10.1109/TCSVT.2018.2864148
• ISSN: 1051-8215

Action recognition with 3D skeleton sequences became popular due to its speed and robustness. The recently proposed convolutional neural networks (CNNs)-based methods show a good performance in learning spatio-temporal representations for skeleton sequences. Despite the good recognition accuracy achieved by previous CNN-based methods, there existed two problems that potentially limit the performance. First, previous skeleton representations were generated by chaining joints with a fixed order. The corresponding semantic meaning was unclear and the structural information among the joints was lost. Second, previous models did not have an ability to focus on informative joints. The attention mechanism was important for skeleton-based action recognition because different joints contributed unequally toward the correct recognition. To solve these two problems, we proposed a novel CNN-based method for skeleton-based action recognition. We first redesigned the skeleton representations with a depth-first tree traversal order, which enhanced the semantic meaning of skeleton images and better preserved the associated structural information. We then proposed the general two-branch attention architecture that automatically focused on spatio-temporal key stages and filtered out unreliable joint predictions. Based on the proposed general architecture, we designed a global long-sequence attention network with refined branch structures. Furthermore, in order to adjust the kernel's spatio-temporal aspect ratios and better capture long-term dependencies, we proposed a sub-sequence attention network (SSAN) that took sub-image sequences as inputs. We showed that the two-branch attention architecture could be combined with the SSAN to further improve the performance. Our experiment results on the NTU RGB+D data set and the SBU kinetic interaction data set outperformed the state of the art. The model was further validated on noisy estimated poses from the subsets of the UCF101 data set and the kinetics data set.