The main aim of this paper is to introduce a novel spatio-temporal model of video matching. This model uses information on image object spatial relationship in frames as well as transition between frames to generate a vector representing that frame. We discuss how these vectors can be generated and matched for video retrieval.
No takes yet. Share an insight, caveat, or question.
Ren et al. (2004) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: