首页> 外文会议>IEEE International Conference on Image Processing >TRANSFER LEARNING WITH DEEP NETWORKS FOR SALIENCY PREDICTION IN NATURAL VIDEO
【24h】

TRANSFER LEARNING WITH DEEP NETWORKS FOR SALIENCY PREDICTION IN NATURAL VIDEO

机译:利用深网络转移学习,在自然视频中的显着性预测

获取原文

摘要

The main purpose of transfer learning is to resolve the problem of different data distribution, generally, when the training samples of source domain are different from the training samples of the target domain. Prediction of salient areas in natural video suffers from the lack of large video benchmarks with human gaze fixations. Different databases only provide dozens up to one or two hundred of videos. The only public large database is HOLLYWOOD with 1707 videos available with gaze recordings. The main idea of this paper is to transfer the knowledge learned with the deep network on a large dataset to train the network on a small dataset to predict salient areas. The results show an improvement on two small publicly available video datasets.
机译:转移学习的主要目的是解决不同数据分布的问题,通常,当源域的训练样本与目标域的训练样本不同时。预测自然视频中的突出区域受到人凝视固定的大型视频基准。不同的数据库只提供数十个或两百个视频。唯一的公共大型数据库是好莱坞,具有1707个视频,凝视录音。本文的主要思想是将知识与大型数据集上的深网络转移到培训网络上的小型数据集以预测突出区域。结果显示了两个小公共视频数据集的改进。

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