OREGON STATE UNIVERSITY

You are here

Human Activities as Stochastic Kronecker Graphs

TitleHuman Activities as Stochastic Kronecker Graphs
Publication TypeConference Paper
Year of Publication2012
AuthorsTodorovic, S.
Conference Name12th European Conference on Computer Vision
Pagination130 - 143
Date Published10/2012
PublisherSpringer Berlin Heidelberg
Conference LocationFlorence, Italy
ISBN Number978-3-642-33709-3
Abstract

A human activity can be viewed as a space-time repetition of activity primitives. Both instances of the primitives, and their repetition are stochastic. They can be modeled by a generative model-graph, where nodes correspond to the primitives, and the graph’s adjacency matrix encodes their affinities for probabilistic grouping into observable video features. When a video of the activity is represented by a graph capturing the space-time layout of video features, such a video graph can be viewed as probabilistically sampled from the activity’s model-graph. This sampling is formulated as a successive Kronecker multiplication of the model’s affinity matrix. The resulting Kronecker-power matrix is taken as a noisy permutation of the adjacency matrix of the video graph. The paper presents our: 1) model-graph; 2) memory- and time-efficient, weakly supervised learning of activity primitives and their affinities; and 3) inference aimed at finding the best expected correspondences between the primitives and observed video features. Our results demonstrate good scalability on UCF50, and superior performance to that of the state of the art on individual, structured, and collective activities of UCF YouTube, Olympic, and Collective datasets.

DOI10.1007/978-3-642-33709-3_10