Optical EngineeringHybrid generative-discriminative human action recognition by combining spatiotemporal words with supervised topic models
|Format||Member Price||Non-Member Price|
We present a hybrid generative-discriminative learning method for human action recognition from video sequences. Our model combines a bag-of-words component with supervised latent topic models. A video sequence is represented as a collection of spatiotemporal words by extracting space-time interest points and describing these points using both shape and motion cues. The supervised latent Dirichlet allocation (sLDA) topic model, which employs discriminative learning using labeled data under a generative framework, is introduced to discover the latent topic structure that is most relevant to action categorization. The proposed algorithm retains most of the desirable properties of generative learning while increasing the classification performance though a discriminative setting. It has also been extended to exploit both labeled data and unlabeled data to learn human actions under a unified framework. We test our algorithm on three challenging data sets: the KTH human motion data set, the Weizmann human action data set, and a ballet data set. Our results are either comparable to or significantly better than previously published results on these data sets and reflect the promise of hybrid generative-discriminative learning approaches.