Unsupervised Semantic Parsing of Video Collections
This addresses the intricate problem of understanding video structure for applications like content analysis and summarization, though it appears incremental as it builds on existing unsupervised parsing methods.
The paper tackles the problem of parsing videos into semantic steps without supervision, using a joint generative model of visual and language cues to produce a storyline and textual descriptions for each step, achieving unprecedented quality on complex YouTube videos.
Human communication typically has an underlying structure. This is reflected in the fact that in many user generated videos, a starting point, ending, and certain objective steps between these two can be identified. In this paper, we propose a method for parsing a video into such semantic steps in an unsupervised way. The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. The proposed method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate this method on a large number of complex YouTube videos and show results of unprecedented quality for this intricate and impactful problem.