@inproceedings{556222b95c1b4b9ab6d10dd7aa1311a6,
title = "Multi-layer linear model for top-down modulation of visual attention in natural egocentric vision",
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.",
keywords = "Ego-centric, Real-world, Visual attention",
author = "Ma, {Keng Teck} and Liyuan Li and Peilun Dai and Lim, {Joo Hwee} and Chengyao Shen and Qi Zhao",
year = "2018",
month = feb,
day = "20",
doi = "10.1109/ICIP.2017.8296927",
language = "English (US)",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3470--3474",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
note = "24th IEEE International Conference on Image Processing, ICIP 2017 ; Conference date: 17-09-2017 Through 20-09-2017",
}