A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：Recently,a new research trend in our video salient object detection(VSOD)research community has focused on enhancing the detection results via model self-fine-tuning using sparsely mined high-quality keyframes from the given sequence.Although such a learning scheme is generally effective,it has a critical limitation,i.e.,the model learned on sparse frames only possesses weak generaliza-tion ability.This situation could become worse on"long"videos since they tend to have intensive scene variations.Moreover,in such videos,the keyframe information from a longer time span is less relevant to the previous,which could also cause learning conflict and de-teriorate the model performance.Thus,the learning scheme is usually incapable of handling complex pattern modeling.To solve this problem,we propose a divide-and-conquer framework,which can convert a complex problem domain into multiple simple ones.First,we devise a novel background consistency analysis(BCA)which effectively divides the mined frames into disjoint groups.Then for each group,we assign an individual deep model on it to capture its key attribute during the fine-tuning phase.During the testing phase,we design a model-matching strategy,which could dynamically select the best-matched model from those fine-tuned ones to handle the giv-en testing frame.Comprehensive experiments show that our method can adapt severe background appearance variation coupling with object movement and obtain robust saliency detection compared with the previous scheme and the state-of-the-art methods.

外文关键词：

Video salient object detectionbackground consistency analysisweakly supervised learninglong-term informationbackground shift

作者：

Yun-Xiao Li、Cheng-Li-Zhao Chen、Shuai Li、Ai-Min Hao、Hong Qin

展开 >

作者单位：

State Key Laboratory of Virtual Reality Technology and Systems,Beihang University,Beijing 100191,China

College of Computer Science and Technology,China University of Petroleum(East China),Qingdao 266580,China

Department of Computer Science,Stony Brook University,New York 11794,USA

基金：

CAMS Innovation Fund for Medical Sciences,ChinaNational Natural Science Foundation of ChinaYouth Innovation and Technology Support Plan of Colleges and Universities in Shandong Province,ChinaNational Science Foundation of USANational Science Foundation of USA

项目编号：

2019-I2M5-016621722462021KJ062IIS-1715985IIS1812606

出版年：

2024

DOI：

10.1007/s11633-023-1388-x

机器智能研究(英文)

中国科学院自动化所

机器智能研究(英文)

CSTPCDEI

影响因子：0.49

ISSN：2731-538X

年,卷(期)：2024.21(4)