利用多尺度迁移学习，通过多级时空双向网络检测视频中的突出物体

IF 1.3 4区计算机科学 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC

IETE Journal of Research Pub Date : 2024-08-05 DOI:10.1080/03772063.2024.2370952

Gaurav Sharma, Maheep Singh, Krishan Berwal

引用次数: 0

摘要

视频显著性预测旨在通过识别视频帧或序列中最相关、最重要的元素来模拟人类的视觉注意力。这项任务在场景中变得尤为复杂...

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Video Salient Object Detection Via Multi-level Spatiotemporal Bidirectional Network Using Multi-scale Transfer Learning

Video saliency prediction aims to resemble human visual attention by identifying the most relevant and significant elements in a video frame or sequence. This task becomes notably intricate in scen...

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IETE Journal of Research 工程技术-电信学

CiteScore

3.30

自引率

6.70%

发文量

308

期刊介绍： IETE Journal of Research is a Bimonthly journal published by the Institution of Electronics and Telecommunication Engineers (IETE), India. It publishes scientific and technical papers describing original research work or novel product/process development. Occasionally special issues are brought out on new and emerging research areas. IETE Journal of Research is useful to researchers, engineers, scientists, teachers, managers and students who are interested in keeping a track of original research and development work being carried out in the broad area of electronics, telecommunications, computer science and engineering and information technology.