.png){kind=icon}
返回
Action class relation detection and classification across multiple video datasets
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2023.08.002.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations enable dataset augmentation, it is only applicable to those covered by MetaVD. For an external dataset to enjoy the same benefit, the relations between its action classes and those in MetaVD need to be determined. To address this issue, we consider two new machine learning tasks: action class relation detection and classification. We propose a unified model to predict relations between action classes, using language and visual information associated with classes. Experimental results show that (i) pre-trained recent neural network models for texts and videos contribute to high predictive performance, (ii) the relation prediction based on action label texts is more accurate than based on videos, and (iii) a blending approach that combines predictions by both modalities can further improve the predictive performance in some cases.
Keyword:
Relation prediction
MetaVD
Human action recognition
Multi-modal classification
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
分享收藏Mercury isotopic composition of igneous rocks from an accretionary orogen: Implications for lithospheric recycling.png)
Geology
OAAI
GeologyIF0
OAAI分享收藏
查看更多内容