Limits...
Self-Organization of Spatio-Temporal Hierarchy via Learning of Dynamic Visual Image Patterns on Action Sequences.

Jung M, Hwang J, Tani J - PLoS ONE (2015)

Bottom Line: Up to now, however, most biological and computational modeling studies have mainly focused on the spatial domain and do not discuss temporal domain processing of the visual cortex.This model is characterized by the application of both spatial and temporal constraints on local neural activities, resulting in the self-organization of a spatio-temporal hierarchy necessary for the recognition of complex dynamic visual image patterns.Furthermore, an evaluation test for the recognition of concatenated sequences of those prototypical movement patterns indicated that the model is endowed with a remarkable capability for the contextual recognition of long-range dynamic visual image patterns.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering, KAIST, Daejeon, Republic of Korea.

ABSTRACT
It is well known that the visual cortex efficiently processes high-dimensional spatial information by using a hierarchical structure. Recently, computational models that were inspired by the spatial hierarchy of the visual cortex have shown remarkable performance in image recognition. Up to now, however, most biological and computational modeling studies have mainly focused on the spatial domain and do not discuss temporal domain processing of the visual cortex. Several studies on the visual cortex and other brain areas associated with motor control support that the brain also uses its hierarchical structure as a processing mechanism for temporal information. Based on the success of previous computational models using spatial hierarchy and temporal hierarchy observed in the brain, the current report introduces a novel neural network model for the recognition of dynamic visual image patterns based solely on the learning of exemplars. This model is characterized by the application of both spatial and temporal constraints on local neural activities, resulting in the self-organization of a spatio-temporal hierarchy necessary for the recognition of complex dynamic visual image patterns. The evaluation with the Weizmann dataset in recognition of a set of prototypical human movement patterns showed that the proposed model is significantly robust in recognizing dynamically occluded visual patterns compared to other baseline models. Furthermore, an evaluation test for the recognition of concatenated sequences of those prototypical movement patterns indicated that the model is endowed with a remarkable capability for the contextual recognition of long-range dynamic visual image patterns.

No MeSH data available.


Related in: MedlinePlus

A sample frame for each action from the Weizmann dataset.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4492609&req=5

pone.0131214.g002: A sample frame for each action from the Weizmann dataset.

Mentions: The Weizmann dataset [19] is provided by the Weizmann Institute of Science for single human action recognition. It contains 90 low resolution (180×144) visual sequences showing 10 human actions (walk, run, jump, gallop sideways, bend, one-hand wave, two-hands wave, jump in place, jumping jack, and skip), each performed by nine subjects (see Fig 2). Each visual sequence is about three seconds long. The view point and background are static.


Self-Organization of Spatio-Temporal Hierarchy via Learning of Dynamic Visual Image Patterns on Action Sequences.

Jung M, Hwang J, Tani J - PLoS ONE (2015)

A sample frame for each action from the Weizmann dataset.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4492609&req=5

pone.0131214.g002: A sample frame for each action from the Weizmann dataset.
Mentions: The Weizmann dataset [19] is provided by the Weizmann Institute of Science for single human action recognition. It contains 90 low resolution (180×144) visual sequences showing 10 human actions (walk, run, jump, gallop sideways, bend, one-hand wave, two-hands wave, jump in place, jumping jack, and skip), each performed by nine subjects (see Fig 2). Each visual sequence is about three seconds long. The view point and background are static.

Bottom Line: Up to now, however, most biological and computational modeling studies have mainly focused on the spatial domain and do not discuss temporal domain processing of the visual cortex.This model is characterized by the application of both spatial and temporal constraints on local neural activities, resulting in the self-organization of a spatio-temporal hierarchy necessary for the recognition of complex dynamic visual image patterns.Furthermore, an evaluation test for the recognition of concatenated sequences of those prototypical movement patterns indicated that the model is endowed with a remarkable capability for the contextual recognition of long-range dynamic visual image patterns.

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering, KAIST, Daejeon, Republic of Korea.

ABSTRACT
It is well known that the visual cortex efficiently processes high-dimensional spatial information by using a hierarchical structure. Recently, computational models that were inspired by the spatial hierarchy of the visual cortex have shown remarkable performance in image recognition. Up to now, however, most biological and computational modeling studies have mainly focused on the spatial domain and do not discuss temporal domain processing of the visual cortex. Several studies on the visual cortex and other brain areas associated with motor control support that the brain also uses its hierarchical structure as a processing mechanism for temporal information. Based on the success of previous computational models using spatial hierarchy and temporal hierarchy observed in the brain, the current report introduces a novel neural network model for the recognition of dynamic visual image patterns based solely on the learning of exemplars. This model is characterized by the application of both spatial and temporal constraints on local neural activities, resulting in the self-organization of a spatio-temporal hierarchy necessary for the recognition of complex dynamic visual image patterns. The evaluation with the Weizmann dataset in recognition of a set of prototypical human movement patterns showed that the proposed model is significantly robust in recognizing dynamically occluded visual patterns compared to other baseline models. Furthermore, an evaluation test for the recognition of concatenated sequences of those prototypical movement patterns indicated that the model is endowed with a remarkable capability for the contextual recognition of long-range dynamic visual image patterns.

No MeSH data available.


Related in: MedlinePlus