首页> 外文会议>IEEE International Conference on Multimedia and Expo >An iterative representation learning framework to predict the sequence of eye fixations
【24h】

An iterative representation learning framework to predict the sequence of eye fixations

机译:迭代表示学习框架,用于预测眼球注视的顺序

获取原文

摘要

Visual attention is a dynamic search process of acquiring information. However, most previous studies have focused on the prediction of static attended locations. Without considering the temporal relationship of fixations, these models usually cannot explain the dynamic saccadic behavior well. In this paper, an iterative representation learning framework is proposed to predict the saccadic scanpath. Within the proposed framework, saccade can be explained as an iterative process of finding the most uncertain area and updating the representation of scenes. In implementation, a deep autoencoder is employed for representation learning. The current fixation is predicted to be the most salient pixel, with saliency estimated by the reconstruction residual of the deep network. Image patches around this fixation are then sampled to update the network for the selection of subsequent fixations. Compared with existing models, the proposed model shows the state-of-the-art performance on several public data sets.
机译:可视注意是获取信息的动态搜索过程。然而,最先前的研究专注于预测静态出席的位置。在不考虑固定的时间关系,这些模型通常无法解决动态扫视行为。在本文中,提出了一种迭代表示学习框架来预测扫视扫描路径。在所提出的框架内,扫视可以被解释为找到最不确定的区域和更新场景的代表的迭代过程。在实现中,使用深度自动频率用于表示学习。预测当前固定是最突出的像素,具有由深网络的重建剩余估计的显着性。然后,对此固定周围的图像修补程序进行采样以更新网络以选择后续固定。与现有型号相比,所提出的模型显示了几种公共数据集上的最先进的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号