JCSE, vol. 15, no. 1, pp.18-33, 2021

DOI: http://dx.doi.org/10.5626/JCSE.2021.15.1.18

A Review of Vision-Based Techniques Applied to Detecting Human-Object Interactions in Still Images

Sunaina, Ramanpreet Kaur, and Dharam Veer Sharma
Department of Computer Science, Punjabi University, Patiala, India

Abstract: Due to the rising demand for automatic interpretation of visual relationships in several domains, human-object interaction (HOI) detection and recognition have also gained more attention from researchers over the last decade. This survey paper concentrates on human-centric interactions, which can be categorized as human-to-human and human-to-objects. Although an extensive amount of research work has been done in this area, real-world constraints like the domain of possible interactions make the research a challenging task. This paper provides an analysis of conventional hand-crafted representation- based methods and recent deep learning-based methods, ongoing advancements taking place in the field of HOI recognition and detection, and challenges faced by the researchers. Moreover, we present a detailed picture of publicly available datasets for HOI evaluations. At the end, the future scope of the study is discussed.

Keyword: Human-object interactions; Action recognition; Visual relationships; Deep learning; Hand crafted; Computer vision

Full Paper:   216 Downloads, 1083 View