Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition

TL;DR

This paper introduces a novel latent semantic learning approach using structured sparse representation and spectral embedding to improve human action recognition by bridging the semantic gap with high-level features.

Contribution

It develops a parameter-free spectral embedding method based on L1-graph with structured sparse coding and hypergraph regularization for better latent semantic discovery.

Findings

Superior performance on KTH dataset

Effective in unconstrained YouTube dataset

Compact and discriminative high-level features

Abstract

This paper proposes a novel latent semantic learning method for extracting high-level features (i.e. latent semantics) from a large vocabulary of abundant mid-level features (i.e. visual keywords) with structured sparse representation, which can help to bridge the semantic gap in the challenging task of human action recognition. To discover the manifold structure of midlevel features, we develop a spectral embedding approach to latent semantic learning based on L1-graph, without the need to tune any parameter for graph construction as a key step of manifold learning. More importantly, we construct the L1-graph with structured sparse representation, which can be obtained by structured sparse coding with its structured sparsity ensured by novel L1-norm hypergraph regularization over mid-level features. In the new embedding space, we learn latent semantics automatically from abundant mid-level features through spectral clustering. The learnt latent semantics can be readily used for human action recognition with SVM by defining a histogram intersection kernel. Different from the traditional latent semantic analysis based on topic models, our latent semantic learning method can explore the manifold structure of mid-level features in both L1-graph construction and spectral embedding, which results in compact but discriminative high-level features. The experimental results on the commonly used KTH action dataset and unconstrained YouTube action dataset show the superior performance of our method.