Human action recognition with structured discriminative random fields

Citations Over TimeTop 15% of 2011 papers

Abstract

Proposed is a structured discriminative random fields model for human action recognition. To represent the human action in a compact but distinct manner, the motion-constrained SIFT (MoSIFT) algorithm is utilised for salient region extraction and description and Bag of Words is sequentially adopted for feature formulation to convert the action sequence into a feature sequence. With this feature representation, a structured discriminative random fields model can be constructed for action modelling and classification. The contribution of the work is to explicitly learn the visual pattern transition between elementary actions to discover the nature of the entire action rather than modelling the gradual change of visual pattern between adjacent frames in traditional methods. A large-scale experiment showed the accuracy and robustness of this method. Moreover, the proposed method outperforms the representative state-of-the-art methods for human action recognition.

Related Papers

• → A 3-dimensional sift descriptor and its application to action recognition(2007)1,616 cited
• → Human action recognition with salient trajectories(2013)37 cited
• → Human Action Recognition using Salient Region Detection in Complex Scenes(2015)11 cited
• Improved Discriminative Model for View- Invariant Human Action Recognition(2013)
• → Human Action Recognition in Still Images Using SIFT Key Points(2022)1 cited