Spatiotemporal Deformable Part Models for Action Detection (Open Access)
Abstract
Deformable part models have achieved impressive performance for object detection, even on difficult image datasets. This paper explores the generalization of deformable part models from 2D images to 3D spatiotemporal volumes to better study their effectiveness for action detection in video. Actions are treated as spatiotemporal patterns and a deformable part model is generated for each action from a collection of examples. For each action model, the most discriminative 3D sub volumes are automatically selected as parts and the spatiotemporal relations between their locations are learned. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to clutter. Extensive experiments on several video datasets demonstrate the strength of spatiotemporal DPMs for classifying and localizing actions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 23, 2013
- Accession Number
- AD1037510
Entities
People
- Mubarak Ali Shah
- Rahul Sukthankar
- Yicong Tian
Organizations
- University of Central Florida