Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video
Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video
复制标题
用于视频中视觉显着性估计的概率多任务学习
DOI：
10.1007/s11263-010-0354-6
复制
发表时间：
2010-11-01
影响因子：
19.5
通讯作者：
Gao, Wen
中科院分区：
文献类型：
--
作者：
Li, Jia;Tian, Yonghong;Gao, Wen
在本文中，我们提出了一种概率的多任务学习方法，用于视频中的视觉显着性估计。在我们的方法中，视觉显着性估计的问题是通过同时考虑概率框架中刺激驱动和任务相关的因素来建模的。在此框架中，刺激驱动的组件使用多尺度小波分解和无偏的特征竞争模拟了人类视觉系统中的低级过程。而与任务相关的组件模拟了高级过程，以偏向输入功能的竞争。与现有方法不同，我们提出了一种多任务学习算法，以学习每个场景的与任务相关的“刺激”映射功能。该算法还学习了各种融合策略，这些策略用于整合刺激驱动的和任务相关的组件以获得视觉显着性。在两个公众眼影数据集和一个区域显着数据集上进行了广泛的实验。实验结果表明，我们的方法的表现非常优于八种最先进的方法。
In this paper, we present a probabilistic multi-task learning approach for visual saliency estimation in video. In our approach, the problem of visual saliency estimation is modeled by simultaneously considering the stimulus-driven and task-related factors in a probabilistic framework. In this framework, a stimulus-driven component simulates the low-level processes in human vision system using multi-scale wavelet decomposition and unbiased feature competition; while a task-related component simulates the high-level processes to bias the competition of the input features. Different from existing approaches, we propose a multi-task learning algorithm to learn the task-related “stimulus-saliency” mapping functions for each scene. The algorithm also learns various fusion strategies, which are used to integrate the stimulus-driven and task-related components to obtain the visual saliency. Extensive experiments were carried out on two public eye-fixation datasets and one regional saliency dataset. Experimental results show that our approach outperforms eight state-of-the-art approaches remarkably.