Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition

Details Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition

2011-09-23

arxiv.org/abs/1109.4979v1

Computer Science

Multimedia

The short version of this paper appears in ICCV 2011

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Latent Semantic Learning with Structured Sparse Representation for Human Action Recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-723830