Multi-layer linear model for top-down modulation of visual attention in natural egocentric vision

Keng Teck Ma, Liyuan Li, Peilun Dai, Joo Hwee Lim, Chengyao Shen, Qi Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages3470-3474
Number of pages5
ISBN (Electronic)9781509021758
DOIs
StatePublished - Feb 20 2018
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: Sep 17 2017Sep 20 2017

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2017-September
ISSN (Print)1522-4880

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period9/17/179/20/17

Keywords

  • Ego-centric
  • Real-world
  • Visual attention

Fingerprint Dive into the research topics of 'Multi-layer linear model for top-down modulation of visual attention in natural egocentric vision'. Together they form a unique fingerprint.

Cite this