.png){kind=icon}
返回
TIVE: A toolbox for identifying video instance segmentation errors
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2023.126321.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we introduce TIVE, a Toolbox for Identifying Video instance segmentation Errors. By directly operating output prediction files, TIVE defines isolated error types and weights each type's dam-age to mAP, for the purpose of distinguishing model characters. By decomposing localization quality in spatial-temporal dimensions, model's potential drawbacks on spatial segmentation and temporal asso-ciation can be revealed. TIVE can also report mAP over instance temporal length for real applications. We conduct extensive experiments by the toolbox to further illustrate how spatial segmentation and temporal association affect each other. We expect the analysis of TIVE can give the researchers more insights, guiding the community to promote more meaningful explorations for video instance segmenta-tion. The proposed toolbox is available at https://github.com/wenhe-jia/TIVE. (c) 2023 Elsevier B.V. All rights reserved.
Keyword:
Video instance segmentation
Error analyzing toolbox
Fine-grained metrics
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
SUNNet: A novel framework for simultaneous human parsing and pose estimationSUNNet: 一种同时进行人体解析和姿态估计的新框架.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏分享收藏分享收藏Chiral cage molecules generated by regioselective O-alkylation of a doubly-bridged calix[8]arene
PREAI
分享收藏
查看更多内容