Limits...
Jointly Learning Multiple Sequential Dynamics for Human Action Recognition.

Liu AA, Su YT, Nie WZ, Yang ZX - PLoS ONE (2015)

Bottom Line: For visual representation, we propose the part-induced spatiotemporal action unit sequence to represent each action sample with multiple partwise sequential feature subspaces.For model learning, we propose the multi-task conditional random fields (MTCRFs) model to discover the sequence-specific structure and the sequence-shared relationship.Specifically, the multi-chain graph structure and the corresponding probabilistic model are designed to represent the interaction among multiple part-induced action unit sequences.

View Article: PubMed Central - PubMed

Affiliation: School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China.

ABSTRACT
Discovering visual dynamics during human actions is a challenging task for human action recognition. To deal with this problem, we theoretically propose the multi-task conditional random fields model and explore its application on human action recognition. For visual representation, we propose the part-induced spatiotemporal action unit sequence to represent each action sample with multiple partwise sequential feature subspaces. For model learning, we propose the multi-task conditional random fields (MTCRFs) model to discover the sequence-specific structure and the sequence-shared relationship. Specifically, the multi-chain graph structure and the corresponding probabilistic model are designed to represent the interaction among multiple part-induced action unit sequences. Moreover we propose the model learning and inference methods to discover temporal context within individual action unit sequence and the latent correlation among different body parts. Extensive experiments are implemented to demonstrate the superiority of the proposed method on two popular RGB human action datasets, KTH & TJU, and the depth dataset in MSR Daily Activity 3D.

No MeSH data available.


Samples from KTH (a), TJU (b), and MDA (c).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4493153&req=5

pone.0130884.g002: Samples from KTH (a), TJU (b), and MDA (c).

Mentions: To achieve the body structure information, we implement two methods for body part localization: 1) For the classic RGB human action datasets, we implement the part model-based method [17] to localize 7 body parts (head, left/right limbs, left/right legs, and left/right feet). Fig 2a shows the samples from KTH. In each image, the big box denotes the localization of human body. The 7 small boxes denote the localized part regions. 2) For the recent datasets recorded by the Kinect sensor, the skeleton data can be directly used for body part localization. Fig 2b and 2c show the samples of the skeleton-based localization results on TJU and MDA.


Jointly Learning Multiple Sequential Dynamics for Human Action Recognition.

Liu AA, Su YT, Nie WZ, Yang ZX - PLoS ONE (2015)

Samples from KTH (a), TJU (b), and MDA (c).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4493153&req=5

pone.0130884.g002: Samples from KTH (a), TJU (b), and MDA (c).
Mentions: To achieve the body structure information, we implement two methods for body part localization: 1) For the classic RGB human action datasets, we implement the part model-based method [17] to localize 7 body parts (head, left/right limbs, left/right legs, and left/right feet). Fig 2a shows the samples from KTH. In each image, the big box denotes the localization of human body. The 7 small boxes denote the localized part regions. 2) For the recent datasets recorded by the Kinect sensor, the skeleton data can be directly used for body part localization. Fig 2b and 2c show the samples of the skeleton-based localization results on TJU and MDA.

Bottom Line: For visual representation, we propose the part-induced spatiotemporal action unit sequence to represent each action sample with multiple partwise sequential feature subspaces.For model learning, we propose the multi-task conditional random fields (MTCRFs) model to discover the sequence-specific structure and the sequence-shared relationship.Specifically, the multi-chain graph structure and the corresponding probabilistic model are designed to represent the interaction among multiple part-induced action unit sequences.

View Article: PubMed Central - PubMed

Affiliation: School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China.

ABSTRACT
Discovering visual dynamics during human actions is a challenging task for human action recognition. To deal with this problem, we theoretically propose the multi-task conditional random fields model and explore its application on human action recognition. For visual representation, we propose the part-induced spatiotemporal action unit sequence to represent each action sample with multiple partwise sequential feature subspaces. For model learning, we propose the multi-task conditional random fields (MTCRFs) model to discover the sequence-specific structure and the sequence-shared relationship. Specifically, the multi-chain graph structure and the corresponding probabilistic model are designed to represent the interaction among multiple part-induced action unit sequences. Moreover we propose the model learning and inference methods to discover temporal context within individual action unit sequence and the latent correlation among different body parts. Extensive experiments are implemented to demonstrate the superiority of the proposed method on two popular RGB human action datasets, KTH & TJU, and the depth dataset in MSR Daily Activity 3D.

No MeSH data available.