Multi-layer linear model for top-down modulation of visual attention in natural egocentric vision
Lists
Only you see this
Abstract
Top-down attention plays an important role in guidance of human attention in real-world scenarios, but less efforts in computational modeing of visual attention has been put on it. Inspired by the mechanisms of top-down attention in human visual perception, we propose a multi-layer linear model of top-down attention to modulate bottom-up saliency maps actively. The first layer is a linear regression model which combines the bottom-up saliency maps on various visual features and objects. A contextual dependent upper layer is introduced to tune the parameters of the lower layer model adaptively. Finally, a mask of selection history is applied to the fused attention map to bias the attention selection towards the task related regions. Efficient learning algorithm with single-pass polynomial complexity is derived. We evaluate our model on a set of natural egocentric videos captured from a wearable glass in real-world environments. Our model outperforms the baseline and state-of-the-art bottom-up saliency models.
BibTeX
@inproceedings{ma2017multi,
author = {Keng Teck Ma and Liyuan Li and Peilun Dai and Joo-Hwee Lim and Chengyao Shen and Qi Zhao},
title = {{Multi-layer linear model for top-down modulation of visual attention in natural egocentric vision}},
booktitle = {ICIP},
year = {2017},
url = {https://openreview.net/forum?id=eLayDrroIs},
}Loading related content...