Real-Time Exact Graph Matching with Application in Human Action Recognition

Çeliktutan, Oya; Wolf, Christian; Sankur, B.; Lombardi, Eric

doi:10.1007/978-3-642-34014-7_2

Cited by 9 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performances of six approaches on each action class are shown in Figure 3. KTH (%) UCF (%) Yeffet et al [24] 90.1 79.2 Wang et al [22] 92.1 85.6 Kovashka et al [11] 94.5 87.3 Le et al [12] 93.9 86.5 Wang et al [21] 94.2 88.2 Jiang et al [10] 95.8 88.0 Wang et al [23] 93.3 -Celiktutan et al [3] 90.6 -Our 'VCG+VSG+CGKs' 97.0 90.7 Table 2. The comparison of our approach with the state-of-the-art approaches on the KTH and UCF sport datasets.…”

Section: Experiments On the Kth Datasetmentioning

confidence: 98%

Human Action Recognition Based on Context-Dependent Graph Kernels

Yuan

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Graphs are a powerful tool to model structured objects, but it is nontrivial to measure the similarity between two graphs. In this paper, we construct a two-graph model to represent human actions by recording the spatial and temporal relationships among local features. We also propose a novel family of context-dependent graph kernels (CGKs) to measure similarity between graphs. First, local features are used as the vertices of the two-graph model and the relationships among local features in the intra-frames and inter-frames are characterized by the edges. Then, the proposed CGKs are applied to measure the similarity between actions represented by the two-graph model. Graphs can be decomposed into numbers of primary walk groups with different walk lengths and our CGKs are based on the context-dependent primary walk group matching. Taking advantage of the context information makes the correctly matched primary walk groups dominate in the CGKs and improves the performance of similarity measurement between graphs. Finally, a generalized multiple kernel learning algorithm with a proposed l12-norm regularization is applied to combine these CGKs optimally together and simultaneously train a set of action classifiers. We conduct a series of experiments on several public action datasets. Our approach achieves a comparable performance to the stateof-the-art approaches, which demonstrates the effectiveness of the two-graph model and the CGKs in recognizing human actions.

show abstract

Section: Experiments On the Kth Datasetmentioning

confidence: 98%

Human Action Recognition Based on Context-Dependent Graph Kernels

Yuan

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…In [3,4], we demonstrated that, in the case of spatio-temporal data, hyper-graph 1 matching problem can be solved with bounded complexity by taking into account the sequential nature of time and causality of human actions. In this work, we customize the same approach for aligning the tracked skeleton sequences.…”

Section: Graph-based Sequence Alignmentmentioning

confidence: 99%

“…In this work, we customize our hyper-graph-based method introduced in [3,4] for aligning the tracked skeleton sequences. We first model the spatio-temporal relationship between the skeleton joints by a chain graphical structure.…”

Section: Introductionmentioning

confidence: 99%

Graph-based analysis of physical exercise actions

Çeliktutan

Akgül

Wolf

et al. 2013

Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Healthcare

Self Cite

View full text Add to dashboard Cite

In this paper, we develop a graph-based method to align two dynamic skeleton sequences, and apply it to both action recognition tasks as well as to the objective quantification of the goodness of the action performance. The automated measurement of "action quality" has potential to be used to monitor action imitations, for example, during a physical therapy. We seek matches between a query sequence and model sequences selected with graph mining. The best matches are obtained through minimizing an energy function that jointly measures space and time domain deformations. This measure has been used for recognizing actions, for separating acceptable and unacceptable action performances, or as a continuous quantification of the action performance goodness. Experimental evaluation demonstrates the improved results of our scheme vis-à-vis its nearest competitors. Furthermore, a plausible relationship has been obtained between action perturbation, given by the joint noise variances, and quality measure, given by matching energies averaged over a sequence.

show abstract

“…In the present volume, Ç eliktutan et al propose an approach to solve the point set matching problem for establishing the correspondence between an action, represented by interest points, to a template [14]. In [15], silhouettes are used for action recognition.…”

Section: Action and Activity Recognitionmentioning

confidence: 99%

Human Behavior Understanding for Robotics

Salah

Ruiz‐del‐Solar²,

Meriçli

et al. 2012

Human Behavior Understanding

View full text Add to dashboard Cite

Abstract. Human behavior is complex, but structured along individual and social lines. Robotic systems interacting with people in uncontrolled environments need capabilities to correctly interpret, predict and respond to human behaviors. This paper discusses the scientific, technological and application challenges that arise from the mutual interaction of robotics and computational human behavior understanding. We supply a short survey of the area to provide a contextual framework and describe the most recent research in this area.

show abstract

Real-Time Exact Graph Matching with Application in Human Action Recognition

Cited by 9 publications

References 36 publications

Human Action Recognition Based on Context-Dependent Graph Kernels

Human Action Recognition Based on Context-Dependent Graph Kernels

Graph-based analysis of physical exercise actions

Human Behavior Understanding for Robotics

Contact Info

Product

Resources

About