2012 · 14 citations · 8 references
ComputingVision ScienceComputer VisionMachine VisionVisual PerceptionFeature DescriptionMotion AnalysisMotion EstimationOptical FlowSupport Vector MachinesVideo AnalysisClassifier FusionFeature-based Optical FlowLegendre PolynomialsOptical Flow EstimationOptical Flow FeaturesSemantic InformationVideo ClassificationVideo Representation Learning
Motion is one of the main characteristics that describe the semantic information of videos. In this work, a global video descriptor based on orientation tensors is proposed. This descriptor is obtained by combining polynomial coefficients calculated for each image in a video. The coefficients are found through the projection of the optical flow on Legendre polynomials, reducing the dimension of per frame motion estimations. The sequence of coefficients are then combined using orientation tensors. The global tensor descriptor created is evaluated by a classification of the KTH video database with a SVM classifier.
8
Recognizing human actions: A local SVM approach
2004 · 2.9K citations
Lihi Zelnik‐Manor, M. Irani · 2005 · 389 citations
Tensor Canonical Correlation Analysis for Action Classification
Tae‐Kyun Kim, Shu-Fai Wong, Roberto Cipolla · 2007 · 326 citations