@article{Lee:2015:10.1109/TIP.2015.2487837,
author = {Lee, K and Ognibene, D and Chang, H and Kim, T-K and Demiris, Y},
doi = {10.1109/TIP.2015.2487837},
journal = {IEEE Transactions on Image Processing},
pages = {5916--5927},
title = {STARE: Spatio-Temporal Attention Relocation for multiple structured activities detection},
url = {http://dx.doi.org/10.1109/TIP.2015.2487837},
volume = {24},
year = {2015}
}

Download

TY  - JOUR
AB  - We present a spatio-temporal attention relocation (STARE) method, an information-theoretic approach for efficient detection of simultaneously occurring structured activities. Given multiple human activities in a scene, our method dynamically focuses on the currently most informative activity. Each activity can be detected without complete observation, as the structure of sequential actions plays an important role on making the system robust to unattended observations. For such systems, the ability to decide where and when to focus is crucial to achieving high detection performances under resource bounded condition. Our main contributions can be summarized as follows: 1) information-theoretic dynamic attention relocation framework that allows the detection of multiple activities efficiently by exploiting the activity structure information and 2) a new high-resolution data set of temporally-structured concurrent activities. Our experiments on applications show that the STARE method performs efficiently while maintaining a reasonable level of accuracy.
AU  - Lee,K
AU  - Ognibene,D
AU  - Chang,H
AU  - Kim,T-K
AU  - Demiris,Y
DO  - 10.1109/TIP.2015.2487837
EP  - 5927
PY  - 2015///
SN  - 1057-7149
SP  - 5916
TI  - STARE: Spatio-Temporal Attention Relocation for multiple structured activities detection
T2  - IEEE Transactions on Image Processing
UR  - http://dx.doi.org/10.1109/TIP.2015.2487837
UR  - https://ieeexplore.ieee.org/document/7293663
UR  - http://hdl.handle.net/10044/1/27670
VL  - 24
ER  - 

Download