2021
DOI: 10.1109/jsen.2021.3098744
|View full text |Cite
|
Sign up to set email alerts
|

Deep Learning for Ballroom Dance Recognition: A Temporal and Trajectory-Aware Classification Model With Three-Dimensional Pose Estimation and Wearable Sensing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 13 publications
(11 citation statements)
references
References 21 publications
0
11
0
Order By: Relevance
“…Results show that it can reach an accuracy of 93%, which far exceeds the baseline of 84.7%. 8 Zhuo Z et al introduced a novel detection method that utilized long and short-term memory and abstract syntax trees to overcome the issue of data steganography blocking attack techniques. This advanced deep learning approach incorporated both contextual and grammatical information to detect such attacks.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…Results show that it can reach an accuracy of 93%, which far exceeds the baseline of 84.7%. 8 Zhuo Z et al introduced a novel detection method that utilized long and short-term memory and abstract syntax trees to overcome the issue of data steganography blocking attack techniques. This advanced deep learning approach incorporated both contextual and grammatical information to detect such attacks.…”
Section: Related Workmentioning
confidence: 99%
“…In Equation (8), G(M i ) represents the generated dance and P i represents the real dance. As the speech synthesis model tacotron2 also introduces an attention mechanism, the study generated the required generator on the basis of this model.…”
Section: Deep Learning Based Generator Discriminator and Self-encoder...mentioning
confidence: 99%
See 1 more Smart Citation
“…[20] compares the performance of DL and traditional ML methods on dance classification with Kinect sensor data. In [16], a neural network is trained to classify 3D pose data from wearable sensors into different ballroom dances. [27] designs a late fusion network for multimodal dance classification, involving four different modalities: RGB frames, optical flows, skeletal data, and audio.…”
Section: Related Workmentioning
confidence: 99%
“…Most existing research on dance recognition focuses on the discrimination of dance types [11,20,27] or the classification of movements in a specific type of dance [2,9,16]. There is a lack of research highlighting the identification of different expressive qualities in improvisational dance.…”
mentioning
confidence: 99%