Main objects interaction activity recognition in real images. Issue 2 (February 2016)

• Record Type: Journal Article
• Authors: Bai, Lin; Li, Kan; Pei, Jianmeng; Jiang, Shuai
• Is Part Of: Neural computing & applications. Volume 27:Issue 2(2016)
• Page Start: 335
• Page End: 348
• Publication Date: 2016-02
• Subjects: Objects interaction activity -- Interesting objects -- Spatial arrangement context -- Image content understanding; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-1846-7
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract 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.