###
Journal of Software:2020.31(7):1969-1979

基于全局和局部信息的视频记忆度预测
王帅,王维莹,陈师哲,金琴
(中国人民大学 信息学院, 北京 100872)
Video Memorability Prediction Based on Global and Local Information
WANG Shuai,WANG Wei-Ying,CHEN Shi-Zhe,JIN Qin
(School of Information, Renmin University of China, Beijing 100872, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 736   Download 356
Received:June 07, 2019    Revised:July 11, 2019
> 中文摘要: 视频的记忆度是一种度量指标,用来表示一段视频能够普遍被人记住的程度.令人记忆深刻而难忘的视频具有很大的潜在价值,因此对能够进行大规模视频记忆度自动预测的模型将会有广大的应用前景和市场,例如视频检索、数字内容推荐、广告设计、教育系统等等.现有的大部分工作都是直接利用深度神经网络学习到的一个全局表示来进行记忆度的预测,没有给予局部细节足够的重视.提出了一个基于全局和局部信息的视频记忆度预测模型,其中,包含3个模块:全局性的上下文表示模块、空间布局表示模块和局部的物体注意力模块.在实验结果中,全局性的上下文表示模块和局部的物体注意力模块分别具有很好的表现.而空间布局表示模块的预测能力虽不如其他两个模块,但3个模块的融合使结果有了进一步的提升.最后,在MediaEval 2018 Media Memorability Prediction Task的数据集上证明了模型的有效性.
Abstract:Memorability of a video is a metric to describe that how memorable the video is. Memorable videos contain huge values and automatically predicting the memorability of large numbers of videos can be applied in various applications including digital content recommendation, advertisement design, education system, and so on. This study proposes a global and local information based framework to predict video memorability. The framework consists of three components, namely global context representation, spatial layout, and local object attention. The experimental results of the global context representation and local object attention are remarkable, and the spatial layout also contributes a lot to the prediction. Finally, the proposedmodel improves the performances of thebaseline of MediaEval 2018 Media Memorability Prediction Task.
文章编号:     中图分类号:TP391    文献标志码:
基金项目:国家自然科学基金(61772535);北京市自然科学基金(4192028);国家重点研发计划(2016YFB1001202) 国家自然科学基金(61772535);北京市自然科学基金(4192028);国家重点研发计划(2016YFB1001202)
Foundation items:National Natural Science Foundation of China (61772535); Beijing Natural Science Foundation (4192028); National Key Research and Development Plan,China (2016YFB1001202)
Reference text:

王帅,王维莹,陈师哲,金琴.基于全局和局部信息的视频记忆度预测.软件学报,2020,31(7):1969-1979

WANG Shuai,WANG Wei-Ying,CHEN Shi-Zhe,JIN Qin.Video Memorability Prediction Based on Global and Local Information.Journal of Software,2020,31(7):1969-1979