ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition

Wan, Jun; Li, Stan Z.; Zhao, Yibing; Zhou, Shuai; Guyon, Isabelle; Escalera, Sérgio

doi:10.1109/cvprw.2016.100

Cited by 220 publications

(154 citation statements)

References 16 publications

Supporting

Mentioning

154

Contrasting

Order By: Relevance

“…To evaluate the effectiveness of the particle filter based probabilistic forced alignment approach we conducted experiments on the popular ChaLearn Continuous Gesture Dataset (ConGD) [31], featured in the 2nd round of the ChaLearn 2017 Continuous Gesture Recognition Challenge. The dataset was formed by re-annotating the ChaLearn 2011 Gesture Dataset [20] to enable evaluation of user-independent recognition.…”

Section: Discussionmentioning

confidence: 99%

“…We apply the proposed method to the continuous gesture recognition problem and evaluate its performance on the challenging large-scale user-independent ChaLearn 2016 Continuous Gesture Recognition (ConGD) dataset [31]. Our method was able to surpass continuous recognition performance of the state-of-the-art [3].…”

Section: Introductionmentioning

confidence: 99%

“…For continuous recognition tasks, datasets with weak annotation commonly provide Sequence Level Annotations that have a sequence of labels for each video that has the temporal ordering information [15]; or Border Level Annotations which are the boundaries between instances in the time domain [31].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Particle Filter Based Probabilistic Forced Alignment for Continuous Gesture Recognition

Camgöz¹,

Hadfield²,

Bowden³

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

In this paper, we propose a novel particle filter based probabilistic forced alignment approach for training spatiotemporal deep neural networks using weak border level annotations.The proposed method jointly learns to localize and recognize isolated instances in continuous streams. This is done by drawing training volumes from a prior distribution of likely regions and training a discriminative 3D-CNN from this data. The classifier is then used to calculate the posterior distribution by scoring the training examples and using this as the prior for the next sampling stage.We apply the proposed approach to the challenging task of large-scale user-independent continuous gesture recognition. We evaluate the performance on the popular ChaLearn 2016 Continuous Gesture Recognition (ConGD) dataset. Our method surpasses state-of-the-art results by obtaining 0.3646 and 0.3744 Mean Jaccard Index Score on the validation and test sets of ConGD, respectively. Furthermore, we participated in the ChaLearn 2017 Continuous Gesture Recognition Challenge and was ranked 3rd. It should be noted that our method is learner independent, it can be easily combined with other approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Particle Filter Based Probabilistic Forced Alignment for Continuous Gesture Recognition

Camgöz¹,

Hadfield²,

Bowden³

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

show abstract

“…The Continuous Gesture Dataset (ConGD) [25], featured by ChaLearn 2016, was designed to evaluate the performance of user-independent gesture recognition methods. The dataset was originally collected for the ChaLearn 2011 Gesture Recognition Challenge [26], but the new protocol was introduced by Wan et al to allow researchers to evaluate their methods for userindependent recognition.…”

Section: Chalearn 2016 Continuous Gesture Datasetmentioning

confidence: 99%

“…In Section III, we give details of the ConGD, which was introduced by Wan et al [25] for the ChaLearn 2016 Large Scale Continuous Gesture Recognition Challenge. In Section IV, we share our experimental setup and results.…”

Section: Introductionmentioning

confidence: 99%

Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition

Camgöz

Hadfield

Koller

et al. 2016

2016 23rd International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Abstract-In this paper, we propose using 3D Convolutional Neural Networks for large scale user-independent continuous gesture recognition. We have trained an end-to-end deep network for continuous gesture recognition (jointly learning both the feature representation and the classifier). The network performs three-dimensional (i.e. space-time) convolutions to extract features related to both the appearance and motion from volumes of color frames. Space-time invariance of the extracted features is encoded via pooling layers. The earlier stages of the network are partially initialized using the work of Tran et al. before being adapted to the task of gesture recognition. An earlier version of the proposed method, which was trained for 11,250 iterations, was submitted to ChaLearn 2016 Continuous Gesture Recognition Challenge and ranked 2nd with the Mean Jaccard Index Score of 0.269235. When the proposed method was further trained for 28,750 iterations, it achieved state-of-the-art performance on the same dataset, yielding a 0.314779 Mean Jaccard Index Score.

show abstract

Literature review of vision‐based dynamic gesture recognition using deep learning techniques

Jain

Karsh

Barbhuiya

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Gesture recognition is the foremost need in building intelligent human‐computer interaction systems to solve many day‐to‐day problems and simplify human life in this digital world. The traditional machine learning (ML) algorithm tried to capture specific handcrafted features, failed miserably in some real‐world environments. Deep learning (DL) techniques have become a sensation among researchers in recent years, making the traditional ML approaches quite obsolete. However, existing reviews consider only a few datasets on which DL algorithm has been applied, and the categorization of the DL algorithms is vague in their review. This study provides the precise categorization of DL algorithms and considers around 15 gesture datasets on which these techniques have been applied. This study also provides a brief overview of the numerous challenging dataset available among the research community and insight into various challenges and limitations of a DL algorithm in vision‐based dynamic gesture recognition.

show abstract

ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition

Cited by 220 publications

References 16 publications

Particle Filter Based Probabilistic Forced Alignment for Continuous Gesture Recognition

Particle Filter Based Probabilistic Forced Alignment for Continuous Gesture Recognition

Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition

Literature review of vision‐based dynamic gesture recognition using deep learning techniques

Contact Info

Product

Resources

About