Temporal Order-Preserving Dynamic Quantization For Human Action Recognition From Multimodal Sensor Streams
Keywords
Human action recognition; Multimodal feature fusion; Temporal dynamic quantization; Temporal order
Abstract
Recent commodity depth cameras have been widely used in the applications of video games, business, surveillance and have dramatically changed the way of human-computer interaction. They provide rich multimodal information that can be used to interpret the human-centric environment. However, it is still of great challenge to model the temporal dynamics of the human actions and great potential can be exploited to further enhance the retrieval accuracy by adequately modeling the patterns of these actions. To address this challenge, we propose a temporal order-preserving dynamic quantization method to extract the most discriminative patterns of the action sequence. We further present a multimodal feature fusion method that can be derived in this dynamic quantization framework to exploit different discriminative capability of features from multiple modalities. Experiments based on three public human action datasets show that the proposed technique has achieved state-of-theart performance.
Publication Date
6-22-2015
Publication Title
ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval
Number of Pages
99-106
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/2671188.2749340
Copyright Status
Unknown
Socpus ID
84962436354 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84962436354
STARS Citation
Ye, Jun; Li, Kai; Hua, Kien A.; and Qi, Guo Jun, "Temporal Order-Preserving Dynamic Quantization For Human Action Recognition From Multimodal Sensor Streams" (2015). Scopus Export 2015-2019. 2087.
https://stars.library.ucf.edu/scopus2015/2087