Human action recognition using Lie Group features and convolutional neural networks

Cai, Linqin; Liu, Chengpeng; Ren, Yuan; Ding, Heen

doi:10.1007/s11071-020-05468-y

Cited by 16 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the cross-subject experiment, 40 types of subjects were divided into training and test sets, numbered as 1, 2, 4, 5, 8, 9, 13,14,15,16,17,18,19,25,27,28,31,34,35,38, and the rest were test sets. In the cross-view experiment, the first camera was selected as the test set, and the rest were training sets.…”

Section: Ntu Rgb-d Datasetmentioning

confidence: 99%

“…From Table 1, it is clear that literature [17] based on variable parameter related skeletons and dynamic skeletons based on 3D geometric relationships) does not take into account deep space-time information, resulting in low accuracy. Literature [18] mapped joints to 3D space and extracted depth features through 3D CNN, thus effectively improving accuracy to 67.96% and 73.69%.…”

Section: Ntu Rgb-d Datasetmentioning

confidence: 99%

Section: Northwestern-ucla Datasetmentioning

confidence: 99%

“…As shown in Table 2, literature [17] assumed that the skeleton was perpendicular to the ground for projection clustering discrimination, ignoring the spatial relationship of the skeleton, resulting in low accuracy. Reference [18] is better than reference [17] because it is based on variable parameter-associated skeleton to represent motions, but it ignores bone dynamic information. Literature [19] obtained 79.72% accuracy by considering the temporal characteristics of joints, but it was difficult to distinguish similar movements due to the lack of appearance information.…”

Section: Northwestern-ucla Datasetmentioning

confidence: 99%

See 3 more Smart Citations

Improved Deep Learning Method for Intelligent Analysis of Sports Training Posture

Yan

2022

Advances in Multimedia

View full text Add to dashboard Cite

Motion recognition based on human bones has attracted extensive attention in recent years because of its simplicity and robustness. Considering the causality of human movement, this paper proposes an improved deep learning method for posture analysis in sports training. In order to deal with the complex situation of calculating joint torques as weights, the edge weights and convolution weights of bone maps are used as auxiliary information networks according to the causality of joint distribution. Thus, the stronger driving force of joint weights in the neural network is improved, the low importance of joint attention is reduced, and the high importance of joint attention is enhanced. Experiments on three public motion recognition datasets show that the proposed method can distinguish similar motions effectively compared with the mainstream methods. Besides, experiments on a challenging UCF (University of Central Florida) sports dataset show that the proposed method can effectively enhance the motion features and improve the accuracy of recognition.

show abstract

Section: Ntu Rgb-d Datasetmentioning

confidence: 99%

Section: Ntu Rgb-d Datasetmentioning

confidence: 99%

Section: Northwestern-ucla Datasetmentioning

confidence: 99%

Section: Northwestern-ucla Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Improved Deep Learning Method for Intelligent Analysis of Sports Training Posture

Yan

2022

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…In addition, we apply an attention mechanism in the decoder to learn good alignments between input and output sequences, guiding the decoder to focus on corresponding parts of the input feature sequences when generating target Laban symbols. Besides, we utilize the Lie group representation proposed in [14,15] and widely used in [13,16,17,18] as input feature for the proposed seq2seq model. In general, by training the encoder and decoder networks together in the proposed seq2seq model, the Labanotation score can be Fig.…”

Section: Introductionmentioning

confidence: 99%

An Attention-Seq2Seq Model Based on CRNN Encoding for Automatic Labanotation Generation from Motion Capture Data

Miao

Zhang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Labanotation is an important notation system widely used for recording dances. Numerous methods have been proposed for automatic Labanotation generation from motion capture data. Recently, the sequence-to-sequence (seq2seq) model is proposed. However, the encoder of the model only encodes the temporal information of motion data, lacking the encoding for spatial information. And it is challenging for the decoder to align input and output sequences due to the imbalance of the sequence lengths. In this paper, we propose an attention-seq2seq model based on Convolutional Recurrent Neural Network (CRNN). The proposed model employs an encoder based on CRNN to learn the spatial-temporal information of motion data and applies an attention mechanism to align each target Laban symbol with relevant parts of the input motion data in decoding. Experiments show that the proposed method performs favorably against state-of-the-art algorithms in the automatic Labanotation generation task.

show abstract

Skeleton-Based Activity Recognition: Preprocessing and Approaches

Sarker

Rahman

Hossain

et al. 2021

Intelligent Systems Reference Library

View full text Add to dashboard Cite

Human action recognition using Lie Group features and convolutional neural networks

Cited by 16 publications

References 33 publications

Improved Deep Learning Method for Intelligent Analysis of Sports Training Posture

Improved Deep Learning Method for Intelligent Analysis of Sports Training Posture

An Attention-Seq2Seq Model Based on CRNN Encoding for Automatic Labanotation Generation from Motion Capture Data

Skeleton-Based Activity Recognition: Preprocessing and Approaches

Contact Info

Product

Resources

About