Latent hierarchical model of temporal structure for complex activity classification
Publication in refereed journal

Times Cited
Altmetrics Information

Other information
AbstractModeling the temporal structure of sub-activities is an important yet challenging problem in complex activity classification. This paper proposes a latent hierarchical model (LHM) to describe the decomposition of complex activity into sub-activities in a hierarchical way. The LHM has a tree-structure, where each node corresponds to a video segment (sub-activity) at certain temporal scale. The starting and ending time points of each sub-activity are represented by two latent variables, which are automatically determined during the inference process. We formulate the training problem of the LHM in a latent kernelized SVM framework and develop an efficient cascade inference method to speed up classification. The advantages of our methods come from: 1) LHM models the complex activity with a deep structure, which is decomposed into sub-activities in a coarse-to-fine manner and 2) the starting and ending time points of each segment are adaptively determined to deal with the temporal displacement and duration variation of sub-activity. We conduct experiments on three datasets: 1) the KTH; 2) the Hollywood2; and 3) the Olympic Sports. The experimental results show the effectiveness of the LHM in complex activity classification. With dense features, our LHM achieves the state-of-the-art performance on the Hollywood2 dataset and the Olympic Sports dataset. © 2013 IEEE.
All Author(s) ListWang L., Qiao Y., Tang X.
Journal nameIEEE Transactions on Image Processing
Volume Number23
Issue Number2
PublisherInstitute of Electrical and Electronics Engineers
Place of PublicationUnited States
Pages810 - 822
LanguagesEnglish-United Kingdom
KeywordsActivity classification, Cascade inference, Deep structure, Hierarchical model, Latent learning

Last updated on 2020-24-09 at 02:24