Abstract
In this paper, we address the problem of recognizing unfinished human activity from partially observed videos. Specifically, we propose a novel human activity descriptor, which can represent pairwise relationships among human activities in a compact manner using pre-trained Convolutional Neural Networks (CNNs) by capturing the discriminative sub-volume. The potentially important relationship among all pairwise sub-volumes, called key-volumes, is automatically captured using global and local motion activation and the ratio of the participant. The captured key-volumes without prior knowledge hold discriminative information related to the unfinished activity. The key-volume information is considered in the descriptor construction procedure. Training a CNN model for a particular purpose requires a lot of resources, such as large amount of labeled data and computing power, despite its representational power. Thus, we develop a method to utilize pre-trained CNN without any additional model training procedure. The low-level features can be extracted through existing CNN toolkits. For a real application, the proposed method may be more cost-effective while implementing a smart surveillance system to understand human activity. In our experiments, we compare the performances of the proposed method with other state-of-the-art human activity prediction methods for two public datasets; the results of the experiments show that the proposed method outperforms these competing methods.
| Original language | English |
|---|---|
| Title of host publication | 2016 23rd International Conference on Pattern Recognition, ICPR 2016 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 2060-2065 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781509048472 |
| DOIs | |
| Publication status | Published - 2017 Apr 13 |
| Event | 23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico Duration: 2016 Dec 4 → 2016 Dec 8 |
Other
| Other | 23rd International Conference on Pattern Recognition, ICPR 2016 |
|---|---|
| Country | Mexico |
| City | Cancun |
| Period | 16/12/4 → 16/12/8 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
Human activity prediction based on Sub-volume Relationship Descriptor. / Lee, Dong Gyu; Lee, Seong Whan.
2016 23rd International Conference on Pattern Recognition, ICPR 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2060-2065 7899939.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Human activity prediction based on Sub-volume Relationship Descriptor
AU - Lee, Dong Gyu
AU - Lee, Seong Whan
PY - 2017/4/13
Y1 - 2017/4/13
N2 - In this paper, we address the problem of recognizing unfinished human activity from partially observed videos. Specifically, we propose a novel human activity descriptor, which can represent pairwise relationships among human activities in a compact manner using pre-trained Convolutional Neural Networks (CNNs) by capturing the discriminative sub-volume. The potentially important relationship among all pairwise sub-volumes, called key-volumes, is automatically captured using global and local motion activation and the ratio of the participant. The captured key-volumes without prior knowledge hold discriminative information related to the unfinished activity. The key-volume information is considered in the descriptor construction procedure. Training a CNN model for a particular purpose requires a lot of resources, such as large amount of labeled data and computing power, despite its representational power. Thus, we develop a method to utilize pre-trained CNN without any additional model training procedure. The low-level features can be extracted through existing CNN toolkits. For a real application, the proposed method may be more cost-effective while implementing a smart surveillance system to understand human activity. In our experiments, we compare the performances of the proposed method with other state-of-the-art human activity prediction methods for two public datasets; the results of the experiments show that the proposed method outperforms these competing methods.
AB - In this paper, we address the problem of recognizing unfinished human activity from partially observed videos. Specifically, we propose a novel human activity descriptor, which can represent pairwise relationships among human activities in a compact manner using pre-trained Convolutional Neural Networks (CNNs) by capturing the discriminative sub-volume. The potentially important relationship among all pairwise sub-volumes, called key-volumes, is automatically captured using global and local motion activation and the ratio of the participant. The captured key-volumes without prior knowledge hold discriminative information related to the unfinished activity. The key-volume information is considered in the descriptor construction procedure. Training a CNN model for a particular purpose requires a lot of resources, such as large amount of labeled data and computing power, despite its representational power. Thus, we develop a method to utilize pre-trained CNN without any additional model training procedure. The low-level features can be extracted through existing CNN toolkits. For a real application, the proposed method may be more cost-effective while implementing a smart surveillance system to understand human activity. In our experiments, we compare the performances of the proposed method with other state-of-the-art human activity prediction methods for two public datasets; the results of the experiments show that the proposed method outperforms these competing methods.
UR - http://www.scopus.com/inward/record.url?scp=85019141877&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019141877&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2016.7899939
DO - 10.1109/ICPR.2016.7899939
M3 - Conference contribution
AN - SCOPUS:85019141877
SP - 2060
EP - 2065
BT - 2016 23rd International Conference on Pattern Recognition, ICPR 2016
PB - Institute of Electrical and Electronics Engineers Inc.
ER -