Concurrence-Aware Long Short-Term Sub-Memories For Person-Person Action Recognition
Abstract
Recently, Long Short-Term Memory (LSTM) has become a popular choice to model individual dynamics for single-person action recognition. However, existing RNN models only focus on capturing the temporal dynamics of the person-person interactions by naively combining the activity dynamics of individuals or modeling them as a whole. This neglects the inter-related dynamics of how person-person interactions change over time. To this end, we propose a novel Concurrent Long Short-Term Memories (Co-LSTM) to model the long-term inter-related dynamics between two interacting people on the bonding boxes covering people. Specifically, for each frame, two sub-memory units store individual motion information, while a concurrent LSTM unit selectively integrates and stores inter-related motion information between interacting people from these two sub-memory units via a new co-memory cell. In experiments, we show the superior performance of Co-LSTM compared with the state-of-the-arts methods.
Publication Date
8-22-2017
Publication Title
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume
2017-July
Number of Pages
2176-2183
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPRW.2017.270
Copyright Status
Unknown
Socpus ID
85030265600 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85030265600
STARS Citation
Shu, Xiangbo; Tang, Jinhui; Qi, Guo Jun; Song, Yan; and Li, Zechao, "Concurrence-Aware Long Short-Term Sub-Memories For Person-Person Action Recognition" (2017). Scopus Export 2015-2019. 7083.
https://stars.library.ucf.edu/scopus2015/7083