Max-Margin Action Prediction Machine
Authors:
- 16 October 2015
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 38 (9) , 1844-1858
Abstract
The speed with which intelligent systems can react to an action depends on how soon it can be recognized. The ability to recognize ongoing actions is critical in many applications, for example, spotting criminal activity. It is challenging, since decisions have to be made based on partial videos of temporally incomplete action executions. In this paper, we propose a novel discriminative multi-scale kernelized model for predicting the action class from a partially observed video. The proposed model captures temporal dynamics of human actions by explicitly considering all the history of observed features as well as features in smaller temporal segments. A compositional kernel is proposed to hierarchically capture the relationships between partial observations as well as the temporal segments, respectively. We develop a new learning formulation, which elegantly captures the temporal evolution over time, and enforces the label consistency between segments and corresponding partial videos. We prove that the proposed learning formulation minimizes the upper bound of the empirical risk. Experimental results on four public datasets show that the proposed approach outperforms state-of-the-art action prediction methods.Keywords
Funding Information
- NSF
- CNS (1314484)
- ONR (N00014-12-1-1028)
- ONR (N00014-14-1-0484)
- NPS (N00244-15-1-0041)
- U.S. Army Research Office Young Investigator (W911NF-14-1-0218)
This publication has 44 references indexed in Scilit:
- Prediction of Human Activity by Discovering Temporal Sequence PatternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Sequential event predictionMachine Learning, 2013
- Complex Events Detection Using Data-Driven Concepts2012
- Activity Forecasting2012
- Action Recognition with Exemplar Based 2.5D Graph Matching2012
- Learning Human Interaction by Interactive Phrases2012
- View-Invariant Action Recognition Using Latent Kernelized Structural SVM2012
- Human Action Segmentation and Recognition Using Discriminative Semi-Markov ModelsInternational Journal of Computer Vision, 2010
- Cutting-plane training of structural SVMsMachine Learning, 2009
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005