arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.12432cs.CV
收藏

所有关于操作的知识图谱

All About Knowledge Graphs for Actions

University of Maryland, College Park(马里兰大学帕克分校)

Pallabi Ghosh, Nirat Saini, Larry S. Davis, Abhinav Shrivastava

摘要:

当前的动作识别系统需要大量的训练数据来识别动作。最近的工作已经探索了zero-shot和少样本学习的范例,以学习未见过的类别或具有很少标签的类别的分类器。在对象识别中遵循类似的范例,这些方法利用外部知识源(例如,来自语言域的知识图谱)。但是,与对象不同,对于动作来说,什么是最好的知识表示还不清楚。在本文中,我们打算获得一个更好的知识图谱(KG),可用于zero-shot和Few-Shot动作识别。特别是,我们研究了三种不同的构建机制:动作嵌入,动作对象嵌入,视觉嵌入。我们提出了广泛的分析不同的KG在不同的实验设置的影响。最后,为了系统地研究zero-shot和Few-Shot方法,我们提出了一种基于UCF 101,HMDB 51和Charades数据集的改进评估范式,用于从Kinetics训练的模型中进行知识转移。

英文摘要:

Current action recognition systems require large amounts of training data for recognizing an action. Recent works have explored the paradigm of zero-shot and few-shot learning to learn classifiers for unseen categories or categories with few labels. Following similar paradigms in object recognition, these approaches utilize external sources of knowledge (eg. knowledge graphs from language domains). However, unlike objects, it is unclear what is the best knowledge representation for actions. In this paper, we intend to gain a better understanding of knowledge graphs (KGs) that can be utilized for zero-shot and few-shot action recognition. In particular, we study three different construction mechanisms for KGs: action embeddings, action-object embeddings, visual embeddings. We present extensive analysis of the impact of different KGs in different experimental setups. Finally, to enable a systematic study of zero-shot and few-shot approaches, we propose an improved evaluation paradigm based on UCF101, HMDB51, and Charades datasets for knowledge transfer from models trained on Kinetics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑