YogaTube: A Video Benchmark for Yoga Action Recognition

Authors: Yadav, S.K., Singh, G., Verma, M., Tiwari, K., Pandey, H.M., Akbar, S.A. and Corcoran, P.

Journal: Proceedings of the International Joint Conference on Neural Networks

Volume: 2022-July

ISBN: 9781728186719

DOI: 10.1109/IJCNN55064.2022.9892122

Abstract:

Yoga can be seen as a set of fitness exercises involving various body postures. Most of the available pose and action recognition datasets are comprised of easy-to-moderate body pose orientations and do not offer much challenge to the learning algorithms in terms of the complexity of pose. In order to observe action recognition from a different perspective, we introduce YogaTube, a new large-scale video benchmark dataset for yoga action recognition. YogaTube aims at covering a wide range of complex yoga postures, which consist of 5484 videos belonging to a taxonomy of 82 classes of yoga asanas. Also, a three-stream architecture has been designed for yoga asanas pose recognition using two modules, feature extraction, and classification. Feature extraction comprises three parallel components. First, pose is estimated using the part affinity fields model to extract meaningful cues from the practitioner. Second, optical flow is used to extract temporal features. Third, raw RGB videos are used for extracting the spatiotemporal features. Finally in the classification module, pose, optical flow, and RGB streams are fused to get the final results of the yoga asanas. To the best of our knowledge, this is the first attempt to establish a video benchmark yoga recognition dataset. The code and dataset will be released soon.

https://eprints.bournemouth.ac.uk/36994/

Source: Scopus

YogaTube: A Video Benchmark for Yoga Action Recognition

Authors: Yadav, S.K., Singh, G., Verma, M., Tiwari, K., Pandey, H.M., Akbar, S.A. and Corcoran, P.

Journal: 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

ISSN: 2161-4393

DOI: 10.1109/IJCNN55064.2022.9892122

https://eprints.bournemouth.ac.uk/36994/

Source: Web of Science (Lite)

YogaTube: A Video Benchmark for Yoga Action Recognition

Authors: Yadav, S., Singh, G., Verma, M., Tiwari, K., Pandey, H., Akbar, S.A. and Corcoran, P.

Conference: WCCI 2022 International Joint Conference on Neural Networks (IJCNN)

Dates: 18-23 July 2022

Publisher: IEEE WCCI2022

Abstract:

Yoga can be seen as a set of fitness exercises involving various body postures. Most of the available pose and action recognition datasets are comprised of easy-to-moderate body pose orientations and do not offer much challenge to the learning algorithms in terms of the complexity of pose. In order to observe action recognition from a different perspective, we introduce YogaTube, a new large-scale video benchmark dataset for yoga action recognition. YogaTube aims at covering a wide range of complex yoga postures, which consist of 5484 videos belonging to a taxonomy of 82 classes of yoga asanas. Also, a three-stream architecture has been designed for yoga asanas pose recognition using two modules, feature extraction, and classification. Feature extraction comprises three parallel components. First, pose is estimated using the part affinity fields model to extract meaningful cues from the practitioner. Second, optical flow is used to extract temporal features. Third, raw RGB videos are used for extracting the spatiotemporal features. Finally in the classification module, pose, optical flow, and RGB streams are fused to get the final results of the yoga asanas. To the best of our knowledge, this is the first attempt to establish a video benchmark yoga recognition dataset. The code and dataset will be released soon.

https://eprints.bournemouth.ac.uk/36994/

Source: Manual

YogaTube: A Video Benchmark for Yoga Action Recognition

Authors: Yadav, S., Singh, G., Verma, M., Tiwari, K., Pandey, H., Akbar, S.A. and Corcoran, P.

Conference: WCCI 2022 International Joint Conference on Neural Networks (IJCNN)

Publisher: IEEE WCCI2022

Abstract:

Yoga can be seen as a set of fitness exercises involving various body postures. Most of the available pose and action recognition datasets are comprised of easy-to-moderate body pose orientations and do not offer much challenge to the learning algorithms in terms of the complexity of pose. In order to observe action recognition from a different perspective, we introduce YogaTube, a new large-scale video benchmark dataset for yoga action recognition. YogaTube aims at covering a wide range of complex yoga postures, which consist of 5484 videos belonging to a taxonomy of 82 classes of yoga asanas. Also, a three-stream architecture has been designed for yoga asanas pose recognition using two modules, feature extraction, and classification. Feature extraction comprises three parallel components. First, pose is estimated using the part affinity fields model to extract meaningful cues from the practitioner. Second, optical flow is used to extract temporal features. Third, raw RGB videos are used for extracting the spatiotemporal features. Finally in the classification module, pose, optical flow, and RGB streams are fused to get the final results of the yoga asanas. To the best of our knowledge, this is the first attempt to establish a video benchmark yoga recognition dataset. The code and dataset will be released soon.

https://eprints.bournemouth.ac.uk/36994/

https://wcci2022.org/

Source: BURO EPrints