基于文本的人重新识别的层次知识导向推理
Ruigeng Zeng1, Wentao Ma2, Tongqing Zhou3
1Laboratory of Digitizing Software for Frontier Equipment, National University of Defence Technology, Changsha, 410073, Hunan, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, 410073, Hunan, China; School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei, 230036, Anhui, China.
本研究介绍了层次知识导向推理 (HKGR),通过使用场景图知识来改善文本-图像人重新识别 (TIReID),以实现更好的视觉-文本对齐,实现最先进的结果.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 蒙面语言建模 (MLM) 已经实现了先进的文本-图像人重新识别 (TIReID),但在随机标记掩盖方面存在困难,阻碍了精确的视觉-文本对齐.
- 目前在TIReID中的MLM方法可能会忽视有效的细粒度对齐所需的语义细微差别,通过平等对待所有子词.
研究的目的:
- 通过在文本中利用层次场景图的知识来增强TIReID,以指导令牌掩盖.
- 为了改善跨模式表示,并克服TIReID的MLM随机代币选择的局限性.
主要方法:
- 提出的等级知识引导推理 (HKGR) 框架利用基于文本场景图形知识的对象,属性和关系级别掩盖.
- 引入了一个多晶体语义对齐 (MGA) 模块,使用令牌选择和相似性分布约束来完善图像-文本对齐.
主要成果:
- 在三个公共基准数据集中,HKGR框架实现了最先进的 (SoTA) 性能.
- 该方法在TIReID任务的所有评估指标上表现出卓越的表现.
结论:
- 在HKGR框架有效地改进TIReID通过结合层次知识为指导视觉-文本对齐.
- 以知识为导向的方法在多模式研究中显示出更广泛应用的前景,包括跨模式检索和视觉问题答案.
更多相关视频
08:25Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
Published on: May 7, 2019
07:35A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
相关概念视频
Deductive Reasoning
For example, a researcher can deduce specific predictions...
Inductive Reasoning
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
Reasoning
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
The Representativeness Heuristic
Reason and Intuition
Methods of Classification and Identification
