Knowledge Commons of Institute of Automation,CAS
A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection | |
Yun-Xiao Li1; Cheng-Li-Zhao Chen1,2; Shuai Li1; Ai-Min Hao1; Hong Qin3 | |
发表期刊 | Machine Intelligence Research
![]() |
ISSN | 2731-538X |
2024 | |
卷号 | 21期号:4页码:684-703 |
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 generalization 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 deteriorate 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 given 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. |
关键词 | Video salient object detection background consistency analysis weakly supervised learning long-term information background shift |
DOI | 10.1007/s11633-023-1388-x |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/58567 |
专题 | 学术期刊_Machine Intelligence Research |
作者单位 | 1.State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191 , China 2.College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China 3.Department of Computer Science, Stony Brook University, New York 11794, USA |
推荐引用方式 GB/T 7714 | Yun-Xiao Li,Cheng-Li-Zhao Chen, Shuai Li,et al. A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection[J]. Machine Intelligence Research,2024,21(4):684-703. |
APA | Yun-Xiao Li,Cheng-Li-Zhao Chen, Shuai Li, Ai-Min Hao,&Hong Qin.(2024).A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection.Machine Intelligence Research,21(4),684-703. |
MLA | Yun-Xiao Li,et al."A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection".Machine Intelligence Research 21.4(2024):684-703. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MIR-2023-11-245.pdf(6454KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论