期刊
IEEE COMPUTER GRAPHICS AND APPLICATIONS
卷 42, 期 6, 页码 37-46出版社
IEEE COMPUTER SOC
DOI: 10.1109/MCG.2022.3201465
关键词
Debugging; Analytical models; Heating systems; Data models; Computational modeling; Activity recognition; Deep learning
资金
- DARPA XAI Program [N66001-17-2-4032]
- NSF award [1900767]
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [1900767] Funding Source: National Science Foundation
This article proposes DETOXER, an interactive visual debugging system, to support finding different error types and scopes in video activity recognition.
In many applications, developed deep-learning models need to be iteratively debugged and refined to improve the model efficiency over time. Debugging some models, such as temporal multilabel classification (TMLC) where each data point can simultaneously belong to multiple classes, can be especially more challenging due to the complexity of the analysis and instances that need to be reviewed. In this article, focusing on video activity recognition as an application of TMLC, we propose DETOXER, an interactive visual debugging system to support finding different error types and scopes through providing multiscope explanations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据