Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach

Liu, Li, Shao, Ling, Li, Xuelong and Lu, Ke (2016) Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach. IEEE Transactions on Cybernetics, 46 (1). pp. 158-170. ISSN 2168-2267

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1109/TCYB.2015.2399172


Extracting discriminative and robust features from video sequences is the first and most critical step in human action recognition. In this paper, instead of using handcrafted features, we automatically learn spatio-temporal motion features for action recognition. This is achieved via an evolutionary method, i.e., genetic programming (GP), which evolves the motion feature descriptor on a population of primitive 3D operators (e.g., 3D-Gabor and wavelet). In this way, the scale and shift invariant features can be effectively extracted from both color and optical flow sequences. We intend to learn data adaptive descriptors for different datasets with multiple layers, which makes fully use of the knowledge to mimic the physical structure of the human visual cortex for action recognition and simultaneously reduce the GP searching space to effectively accelerate the convergence of optimal solutions. In our evolutionary architecture, the average cross-validation classification error, which is calculated by an support-vector-machine classifier on the training set, is adopted as the evaluation criterion for the GP fitness function. After the entire evolution procedure finishes, the best-so far solution selected by GP is regarded as the (near-)optimal action descriptor obtained. The GP-evolving feature extraction method is evaluated on four popular action datasets, namely KTH, HMDB51, UCF YouTube, and Hollywood2. Experimental results show that our method significantly outperforms other types of features, either hand-designed or machine-learned.

Item Type: Article
Uncontrolled Keywords: Action recognition, feature extraction, feature learning, genetic programming (GP), spatio-temporal descriptors
Subjects: G400 Computer Science
G700 Artificial Intelligence
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: Paul Burns
Date Deposited: 10 Jun 2015 09:30
Last Modified: 12 Oct 2019 22:59
URI: http://nrl.northumbria.ac.uk/id/eprint/22802

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics