Finding Causal Interactions in Video Sequences
Presenters:
Lead Presenter: Caglayan Dicle
Additional Presenters: Mustafa Ayazoglu
Faculty Advisor/Principal Investigator: Octavia Camps
Method of Presentation: Poster
Details:
Year: 2012
University Research Theme: Security
Abstract:
This paper considers the problem of detecting causal in- teractions in video clips. Specifically, the goal is to detect whether the actions of a given target can be explained, in a sense that we make explicit in the paper, in terms of the past actions of other agents. We propose to solve this problem by recasting it into a directed graph topology identification, where each node corresponds to the observed motion of a given target, and each link indicates the presence of a causal correlation. As shown in the paper, this leads to a block-sparsification problem that can be efficiently solved using a Group-Lasso type approach, combined with a re-weighted heuristics. These results are illustrated with several examples involving non