Higher order motion models and spectral clustering
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 614-621
Abstract
Motion segmentation based on point trajectories can integrate information of a whole video shot to detect and separate moving objects. Commonly, similarities are defined between pairs of trajectories. However, pairwise similarities restrict the motion model to translations. Non-translational motion, such as rotation or scaling, is penalized in such an approach. We propose to define similarities on higher order tuples rather than pairs, which leads to hypergraphs. To apply spectral clustering, the hypergraph is transferred to an ordinary graph, an operation that can be interpreted as a projection. We propose a specific nonlinear projection via a regularized maximum operator, and show that it yields significant improvements both compared to pairwise similarities and alternative hypergraph projections.Keywords
This publication has 15 references indexed in Scilit:
- Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions2011
- Visual Parsing After Recovery From BlindnessPsychological Science, 2009
- Learning the Shared Subspace for Multi-task Clustering and Transductive Transfer Classification2009
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- Higher-order clique reduction in binary graph cut2009
- Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories2008
- P3 & Beyond: Solving Energies with Higher Order Cliques2007
- Higher order learning with graphs2006
- Beyond Pairwise Clustering2005
- Recent directions in netlist partitioning: a surveyIntegration, 1995