A Video Representation Method Based on Multi-View Structure Preserving Embedding for Action Retrieval

Abstract

The content-based video retrieval is a popular topic in computer vision filed, especially, action retrieval. This paper proposes a novel and effective video representation module for content-based action retrieval framework, in which feature learning can be conducted with complementary information and intrinsic structure, where the relationship between appearance feature and geometry can be preserved. Based on multi-view analysis and graph embedding, the target features are generated to minimize the inter-class discrepancy and maximize intra-class discrimination. Applied to the content-based retrieval task, the proposed method can be combined with Euclidean distance for the comparison of low-dimensional features. As demonstrated in the extensive experiments on the benchmark datasets, the performance of the proposed framework is superior to the state-of-the-art methods.

Keywords

• Action retrieval
• video representation
• multi-view analysis
• graph embedding