Main objects interaction activity recognition in real images

Lin Bai*, Kan Li, Jianmeng Pei, Shuai Jiang

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

12 引用 (Scopus)
Plum Print visual indicator of research metrics
  • Citations
    • Citation Indexes: 12
  • Captures
    • Readers: 9
see details

摘要

Automatically describing the image caption is a challenging task in computer vision. The difficulty mainly lies in capturing the interesting objects and recognizing the interaction activity of the interesting objects. In this paper, we introduce “centerpiece interaction,” a complex visual composite, to represent the main objects interaction activity. We propose a centerpiece interaction recognition framework to achieve the detection of interesting objects and the recognition of their interaction activity by regarding them as an integrated task. In our framework, firstly, a graph-based model is proposed to learn the 2.5D spatial co-occurrence context among objects, which strongly facilitates the interesting objects detection. Secondly, we propose a hierarchical model, with the help of 2.5D spatial co-occurrence context obtained, to learn the relational features of the interesting objects in a hierarchy of stages by integrating the features of the interesting objects, which significantly improve the recognition of centerpiece interaction. Experiments on a joint dataset show that our framework outperforms state-of-the-art in spatial co-occurrence context analysis, the interesting objects detection and the centerpiece interaction recognition.

源语言英语
页(从-至)335-348
页数14
期刊Neural Computing and Applications
27
2
DOI
出版状态已出版 - 1 2月 2016

指纹

探究 'Main objects interaction activity recognition in real images' 的科研主题。它们共同构成独一无二的指纹。

引用此

Bai, L., Li, K., Pei, J., & Jiang, S. (2016). Main objects interaction activity recognition in real images. Neural Computing and Applications, 27(2), 335-348. https://doi.org/10.1007/s00521-015-1846-7