EAGER: Visual Saliency with Discriminancy, Sparsity and Connectivity

EAGER：具有辨别力、稀疏性和连通性的视觉显着性

• 批准号: 1152576
• 负责人: Ming-Hsuan Yang
• 金额: $ 13.57万
• 依托单位: University of California - Merced
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-01-01 至 2015-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1152576&HistoricalAwards=false
• 关键词: EAGER; Visual; Saliency; Discriminancy; Sparsity

This project explores new directions to solving top-down modulated visual saliency maps with three basic principles: discriminancy, sparsity and connectivity. The research identifies key factors for advancing the state-of-the-art and presents a novel latent variable model, which extends the classical conditional random field with an embedded layer of latent variables to exploit the sparsity nature of features for saliency maps. This sparse latent variable conditional random filed model can be considered as a joint optimization of group sparse coding and conditional random field, which can be solved with an efficient stochastic gradient descent algorithm. Unlike bottom-up saliency, this model facilities high-level visual recognition tasks by learning sparse image structures from objects of interest. The key intellectual contributions of this project are a novel formulation that considers all three important properties for visual saliency in a unified framework, and an efficient learning algorithm to estimate the model parameters. With the developed techniques, the search regions of these vision tasks can be constrained and thereby reduce the computational complexity and enhancing robustness. Effective top-down modulated visual saliency algorithms have broad applications including object detection, object recognition, visual tracking, scene analysis, image compression, surveillance, and robotics. It also provides a crucial tool for studying and analyzing fixations of eye movements in cognitive science. The research results including code and data are made public on the project web site.

这个项目探索了解决自上而下调制视觉显着图的新方向，有三个基本原则：判别性，稀疏性和连通性。该研究确定了推进最先进技术的关键因素，并提出了一种新的潜变量模型，该模型扩展了经典的条件随机场，嵌入了一层潜变量，以利用显着性图特征的稀疏性。该稀疏隐变量条件随机场模型可以看作是分组稀疏编码和条件随机场的联合优化问题，可以用一种有效的随机梯度下降算法求解。 与自下而上的显着性不同，该模型通过从感兴趣的对象中学习稀疏图像结构来实现高级视觉识别任务。该项目的主要智力贡献是一个新的配方，认为所有三个重要属性的视觉显着性在一个统一的框架，和一个有效的学习算法来估计模型参数。与发达国家的技术，这些视觉任务的搜索区域可以被约束，从而降低了计算复杂度和增强鲁棒性。有效的自顶向下调制视觉显著性算法具有广泛的应用，包括目标检测，目标识别，视觉跟踪，场景分析，图像压缩，监视和机器人。它也为认知科学中研究和分析眼动注视提供了重要工具。研究结果包括代码和数据在项目网站上公开。