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.


ROC and AUC of TJU with different hidden states.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0130884.g005: ROC and AUC of TJU with different hidden states.

Mentions: With the ST-AUS representation, the proposed MTCRFs model can be trained and utilized for action recognition based on the Maximum A Posteriori criteria. To select the best hidden state for temporal modeling, we plotted the ROC curve of each hidden state number and the best parameter can be selected when the area under curve (AUC) of the corresponding ROC reached the maximum. In our experiments, we varied the number of hidden states from 3 to 6 per chain for parameter selection. From Figs 4, 5 and 6, it is obvious that the MTCRFs model on each dataset can achieve the best performance with hidden_state = 5.


Jointly Learning Multiple Sequential Dynamics for Human Action Recognition.

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

ROC and AUC of TJU with different hidden states.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0130884.g005: ROC and AUC of TJU with different hidden states.
Mentions: With the ST-AUS representation, the proposed MTCRFs model can be trained and utilized for action recognition based on the Maximum A Posteriori criteria. To select the best hidden state for temporal modeling, we plotted the ROC curve of each hidden state number and the best parameter can be selected when the area under curve (AUC) of the corresponding ROC reached the maximum. In our experiments, we varied the number of hidden states from 3 to 6 per chain for parameter selection. From Figs 4, 5 and 6, it is obvious that the MTCRFs model on each dataset can achieve the best performance with hidden_state = 5.

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.