Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos

23 Mar 2016  ·  Amir Shahroudy, Tian-Tsong Ng, Yihong Gong, Gang Wang ·

Single modality action recognition on RGB or depth sequences has been extensively explored recently. It is generally accepted that each of these two modalities has different strengths and limitations for the task of action recognition. Therefore, analysis of the RGB+D videos can help us to better study the complementary properties of these two types of modalities and achieve higher levels of performance. In this paper, we propose a new deep autoencoder based shared-specific feature factorization network to separate input multimodal signals into a hierarchy of components. Further, based on the structure of the features, a structured sparsity learning machine is proposed which utilizes mixed norms to apply regularization within components and group selection between them for better classification performance. Our experimental results show the effectiveness of our cross-modality feature analysis framework by achieving state-of-the-art accuracy for action classification on five challenging benchmark datasets.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multimodal Activity Recognition MSR Daily Activity3D dataset DSSCA-SSLM (RGB+D) Accuracy 97.5 # 1
Action Recognition NTU RGB+D DSSCA-SSLM (RGB only) Accuracy (CS) 74.9 # 16

Methods


No methods listed for this paper. Add relevant methods here