What do different evaluation metrics tell us about saliency models?

Z Bylinskii, T Judd, A Oliva, A Torralba… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
How best to evaluate a saliency model's ability to predict where humans look in images is an
open research question. The choice of evaluation metric depends on how saliency is …

[PDF][PDF] 引入视觉注意机制的目标跟踪方法综述

黎万义, 王鹏, 乔红 - 自动化学报, 2014 - aas.net.cn
摘要视觉跟踪在无人飞行器, 移动机器人, 智能监控等领域有着广泛的应用,
但由于目标外观和环境的变化, 以及背景干扰等因素的存在, 使得复杂场景下的鲁棒实时的目标 …

State-of-the-art in visual attention modeling

A Borji, L Itti - IEEE transactions on pattern analysis and …, 2012 - ieeexplore.ieee.org
Modeling visual attention-particularly stimulus-driven, saliency-based attention-has been a
very active research area over the past 25 years. Many different models of attention are now …

Quantitative analysis of human-model agreement in visual saliency modeling: A comparative study

A Borji, DN Sihite, L Itti - IEEE Transactions on Image …, 2012 - ieeexplore.ieee.org
Visual attention is a process that enables biological and machine vision systems to select
the most relevant regions from a scene. Relevance is determined by two components: 1) top …

Adaptive object tracking by learning background context

A Borji, S Frintrop, DN Sihite, L Itti - 2012 IEEE computer society …, 2012 - ieeexplore.ieee.org
One challenge when tracking objects is to adapt the object representation depending on the
scene context to account for changes in illumination, coloring, scaling, etc. Here, we present …

Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features

HR Tavakoli, A Borji, J Laaksonen, E Rahtu - Neurocomputing, 2017 - Elsevier
This paper presents a novel fixation prediction and saliency modeling framework based on
inter-image similarities and ensemble of Extreme Learning Machines (ELM). The proposed …

Flame detection algorithm based on a saliency detection technique and the uniform local binary pattern in the YCbCr color space

ZG Liu, Y Yang, XH Ji - Signal, Image and Video Processing, 2016 - Springer
Computer vision-based fire detection involves flame detection and smoke detection. This
paper proposes a new flame detection algorithm that is based on a saliency detection …

Adaptive real-time video-tracking for arbitrary objects

DA Klein, D Schulz, S Frintrop… - 2010 IEEE/RSJ …, 2010 - ieeexplore.ieee.org
In this paper, we present a visual object tracker for mobile systems that is able to specialize
to individual objects during tracking. The core of our method is a novel observation model …

Visual attention-based image watermarking

D Bhowmik, M Oakes, C Abhayaratne - IEEE Access, 2016 - ieeexplore.ieee.org
Imperceptibility and robustness are two complementary but fundamental requirements of
any watermarking algorithm. Low strength watermarking yields high imperceptibility but …

[PDF][PDF] From the human visual system to the computational models of visual attention: a survey

S Filipe, LA Alexandre - Artificial Intelligence Review, 2013 - Citeseer
With the emerging interest in active vision, computer vision researchers have been
increasingly concerned with the mechanisms of attention. Therefore, a number of visual …