G3D: A gaming action dataset and real time action recognition evaluation framework

Bloom, Victoria; Makris, Dimitrios; Argyriou, Vasileios

doi:10.1109/cvprw.2012.6239175

Cited by 201 publications

(149 citation statements)

References 8 publications

Supporting

Mentioning

147

Contrasting

Order By: Relevance

“…AdaBoost, Bloom et al [44] 0.585 SVM + SW, Li et al [32] 0.767 Deep RNN + SW, Li et al [32] 0.833 Deep CA-RNN, Li et al [32] 0.940 Deep JCR-RNN, Li et al [32] 0.962 These results are consistent with previous experiments. Specifically, the proposed CuDi3D approach performs better than state-of-the-art methods on the G3D dataset with a detection score of 98.7% according to this fixed split protocol.…”

Section: F Scoresupporting

confidence: 85%

“…Specifically, the proposed CuDi3D approach performs better than state-of-the-art methods on the G3D dataset with a detection score of 98.7% according to this fixed split protocol. Compared to previous sliding windows approaches with fixed sizes such as the ones proposed in [44,32], the obtained results confirm the superiority of our approach which is much more adapted for handling temporal variabilities. These results are particularly important as they testify the superiority of our approach against more complex systems like the deep RNN based ones presented in [32].…”

Section: F Scoresupporting

confidence: 66%

“…In particular, we conduct an extensive experimental study with the proposed approach and provide a comparison with twelve state-of-the-art OAD algorithms [19,8,5,9,20,15,44,14,32,16,17,7] on three skeleton-based datasets, MSRC-12 [8], G3D [44] and MAD [16].…”

Section: Experimental Evaluation and Discussionmentioning

confidence: 99%

“…G3D aims at allowing the development of new action detection and recognition algorithms for video games [44]. It is a set of 20 gaming actions performed by 10 subjects who were given basic instructions as to how to perform the action.…”

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

“…Following [44] we split data by subjects such that the first 5 subjects were used for training and the remaining 5 subjects for testing. The results are shown in Table 8.…”

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

See 4 more Smart Citations

CuDi3D: Curvilinear displacement based approach for online 3D action detection

Boulahia

Anquetil

Multon

et al. 2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

To cite this version:Said Yacine Boulahia, Eric Anquetil, Franck Multon, Richard Kulpa. CuDi3D: Curvilinear displacement based approach for online 3D action detection. Computer Vision and Image Understanding, Elsevier, 2018, 174, pp.57-69 AbstractBeing able to interactively detect and recognize 3D actions based on skeleton data, in unsegmented streams, has become an important computer vision topic. It raises three scientific problems in relation with variability. The first one is the temporal variability that occurs when subjects perform gestures with different speeds. The second one is the inter-class spatial variability, which refers to disparities between the displacement amounts induced by different classes (i.e. long vs. short movements). The last one is the intra-class spatial variability caused by differences in style and gesture amplitude. In this paper, we design an original approach that better considers these three issues. To address temporal variability we introduce the notion of curvilinear segmentation. It consists in extracting features, not on temporally-based sliding windows, but on trajectory segments for which the cumulated displacement equals a class-based amount. Second, to tackle inter-class spatial variability, we define several competing classifiers with their dedicated curvilinear windows. Last, we address intra-class spatial variability by designing a fusion system that takes the decisions and confidence scores of every competing classifier into account. Extensive experiments on four challenging skeleton-based datasets demonstrate the relevance of the proposed approach for action recognition and online action detection.

show abstract

Section: F Scoresupporting

confidence: 85%

Section: F Scoresupporting

confidence: 66%

Section: Experimental Evaluation and Discussionmentioning

confidence: 99%

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

“…Following [44] we split data by subjects such that the first 5 subjects were used for training and the remaining 5 subjects for testing. The results are shown in Table 8.…”

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

See 3 more Smart Citations

CuDi3D: Curvilinear displacement based approach for online 3D action detection

Boulahia

Anquetil

Multon

et al. 2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

Registration for Motion Estimation and Object Tracking

Argyriou

Rincón

Villarini

et al. 2015

Image, Video &Amp; 3D Data Registration

View full text Add to dashboard Cite

Dance performance evaluation using hidden Markov models

Laraba

Tilmanne

2016

Computer Animation & Virtual

View full text Add to dashboard Cite

We present in this paper a hidden Markov model-based system for real-time gesture recognition and performance evaluation. The system decodes performed gestures and outputs at the end of a recognized gesture, a likelihood value that is transformed into a score. This score is used to evaluate a performance comparing to a reference one. For the learning procedure, a set of relational features has been extracted from high-precision motion capture system and used to train hidden Markov models. At runtime, a low-cost sensor (Microsoft Kinect) is used to capture a learner's movements. An intermediate step of model adaptation was hence requested to allow recognizing gestures captured by this low-cost sensor. We present one application of this gesture evaluation system in the context of traditional dance basics learning. The estimation of the log-likelihood allows giving a feedback to the learner as a score related to his performance.

show abstract

G3D: A gaming action dataset and real time action recognition evaluation framework

Cited by 201 publications

References 8 publications

CuDi3D: Curvilinear displacement based approach for online 3D action detection

CuDi3D: Curvilinear displacement based approach for online 3D action detection

Registration for Motion Estimation and Object Tracking

Dance performance evaluation using hidden Markov models

Contact Info

Product

Resources

About