A Videography Analysis Framework for Video Retrieval and Summarization (Open Access)

摘要: Abstract : In this work, we focus on developing features and approaches to represent analyze videography styles in unconstrained videos. By videos, mean typical consumer videos with significant content complexity diverse editing artifacts, mostly long duration. Our approach constructs a dictionary, which is used each video clip as series of varying words. addition conventional such camera motion foreground object motion, two novel including correlation scale information are introduced characterize videography. Then, show that unique signatures from different events can be automatically identified, using statistical analysis methods. For practical applications, explore the use for content-based retrieval summarization. We compare our other methods large dataset, demonstrate benefits analysis.