Action categorization by structural probabilistic latent semantic analysis

Jianguo Zhang, Shaogang Gong

    Research output: Contribution to journalArticlepeer-review

    36 Citations (Scopus)


    Temporal dependency is a very important cue for modeling human actions. However, approaches using latent topics models, e.g., probabilistic latent semantic analysis (pLSA), employ the bag of words assumption therefore word dependencies are usually ignored. In this work, we propose a new approach structural pLSA (SpLSA) to model explicitly word orders by introducing latent variables. More specifically, we develop an action categorization approach that learns action representations as the distribution of latent topics in an unsupervised way, where each action frame is characterized by a codebook representation of local shape context. The effectiveness of this approach is evaluated using both the WEIZMANN dataset and the MIT dataset. Results show that the proposed approach outperforms the standard pLSA. Additionally, our approach is compared favorably with six existing models including GMM, logistic regression, HMM, SVM, CRF, and HCRF given the same feature representation. These comparative results show that our approach achieves higher categorization accuracy than the five existing models and is comparable to the state-of-the-art hidden conditional random field based model using the same feature set.

    Original languageEnglish
    Pages (from-to)857-864
    Number of pages8
    JournalComputer Vision and Image Understanding
    Issue number8
    Publication statusPublished - 2010


    Dive into the research topics of 'Action categorization by structural probabilistic latent semantic analysis'. Together they form a unique fingerprint.

    Cite this