Hierarchical Self-organizing Maps System for Action Classification

Gharaee, Zahra; Gärdenfors, Peter; Johnsson, Magnus

doi:10.5220/0006199305830590

Cited by 8 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of the experiments performed in this study show that the recognition of unsegmented actions in online test experiments is quite high. When the performance results of this paper are compared to our earlier empirical studies, whether they are online experiments (Gharaee et al 2016(Gharaee et al , 2017c or offline experiments (Gharaee et al 2017b, a), there is a decrease in the acquired recognition accuracy of the system. An explanation for this may be that different sequences of actions span different time intervals, while a constant cutoff length is allocated to all of them through the sliding window.…”

Section: Discussionmentioning

confidence: 90%

“…For this, it is necessary that the sliding window contains the key activations of an action sequence continuously for a number of consecutive iterations, which is a restriction for the categorization task. The 75% correct categorizations should be compared to 83% correct that was obtained (Gharaee et al 2017b) when the dataset was segmented in advance in an offline experiment. The results show that the performance drops when the segmented action pattern vector of fixed length is used, but at the same time the system is capable of running online experiments.…”

Section: Methodsmentioning

confidence: 99%

“…There are several other applications for action recognition systems including human-computer interaction, video retrieval, sign language recognition, medical health care, video analysis (sports video analysis), game industry and video surveillance. In earlier works (Gharaee et al 2016(Gharaee et al , 2017b, a, c; Gharaee 2018a), Gharaee et al developed a system for human action recognition using hierarchical architecture based on self-organizing neural networks. Recently this architecture is developed by using growing grid networks to improve its perfomance in recognizing human actions (Gharaee 2018b(Gharaee , 2020.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online recognition of unsegmented actions with hierarchical SOM architecture

Gharaee

2020

Cogn Process

Self Cite

View full text Add to dashboard Cite

Automatic recognition of an online series of unsegmented actions requires a method for segmentation that determines when an action starts and when it ends. In this paper, a novel approach for recognizing unsegmented actions in online test experiments is proposed. The method uses self-organizing neural networks to build a three-layer cognitive architecture. The unique features of an action sequence are represented as a series of elicited key activations by the first-layer self-organizing map. An average length of a key activation vector is calculated for all action sequences in a training set and adjusted in learning trials to generate input patterns to the second-layer self-organizing map. The pattern vectors are clustered in the second layer, and the clusters are then labeled by an action identity in the third layer neural network. The experiment results show that although the performance drops slightly in online experiments compared to the offline tests, the ability of the proposed architecture to deal with the unsegmented action sequences as well as the online performance makes the system more plausible and practical in real-case scenarios.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online recognition of unsegmented actions with hierarchical SOM architecture

Gharaee

2020

Cogn Process

Self Cite

View full text Add to dashboard Cite

show abstract

“…This can be accomplished by basically the same psychological methods used for investigating similarities between objects. In robotics, a common method for reducing the complexity of an action is to use a Kinect sensor that extracts the movements of a stick-figure representation of a person and then use a neural network to classify the reduced actions (e.g., References [43,44]). An analogy between how objects and how actions are represented in conceptual spaces is that action concepts share a similar structure with object categories; in particular, they have prototypes [45].…”

Section: Actionsmentioning

confidence: 99%

“…These systems are psychologically motived, and they have not been developed with the aim of supporting human-robot communication. Recent computational work by Gharaee and her colleagues has resulted in an online system based on neural networks that can categorize and segment a number of bodily actions [43,44,48]. Such a system can be used by a robot to select a relevant verb (see Section 4.3) to be used in the robot's construction of sentences describing what is happening.…”

Section: Actionsmentioning

confidence: 99%

Using Event Representations to Generate Robot Semantics

Gärdenfors

2019

J. Hum.-Robot Interact.

Self Cite

View full text Add to dashboard Cite

Most semantic models employed in human-robot interactions concern how a robot can understand commands, but in this article the aim is to present a framework that allows dialogic interaction. The key idea is to use events as the fundamental structures for the semantic representations of a robot. Events are modeled in terms of conceptual spaces and mappings between spaces. It is shown how the semantics of major word classes can be described with the aid of conceptual spaces in a way that is amenable to computer implementations. An event is represented by two vectors, one force vector representing an action and one result vector representing the effect of the action. The two-vector model is then extended by the thematic roles so an event is built up from an agent, an action, a patient, and a result. It is shown how the components of an event can be put together to semantic structures that represent the meanings of sentences. It is argued that a semantic framework based on events can generate a general representational framework for humanrobot communication. An implementation of the framework involving communication with an iCub will be described.

show abstract