HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos


This paper addresses the problem of recognizing and localizing coherent activities of a group of people, called collective activities, in video. Related work has argued the benefits of capturing long-range and higher-order dependencies among video features for robust recognition. To this end, we formulate a new deep model, called Hierarchical Random Field (HiRF). HiRF models only hierarchical dependencies between model variables. This effectively amounts to modeling higher-order temporal dependencies of video features. We specify an efficient inference of HiRF that iterates in each step linear programming for estimating latent variables. Learning of HiRF parameters is specified within the max-margin framework. Our evaluation on the benchmark New Collective Activity and Collective Activity datasets, demonstrates that HiRF yields superior recognition and localization as compared to the state of the art.

DOI: 10.1007/978-3-319-10599-4_37

Extracted Key Phrases

11 Figures and Tables

Citations per Year

Citation Velocity: 14

Averaging 14 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@inproceedings{Amer2014HiRFHR, title={HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos}, author={Mohamed R. Amer and Peng Lei and Sinisa Todorovic}, booktitle={ECCV}, year={2014} }