Evaluation of Deep Learning CNN Model for Recognition of Devanagari Digit

Bhosle, Kavita; Musande, Vijaya

doi:10.47852/bonviewaia3202441

Cited by 31 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 The main idea is to introduce attention weights and construct a content vector. The content vector is calculated as shown in Equation (5).…”

Section: Design Of Deep Learning-based Feature Extraction Methodsmentioning

confidence: 99%

“…4 However, deep learning-based dance models also have certain problems, such as the model-generated dances do not match the music well, the model-generated dances are not complete enough, and the fluency and rationality of long dances are not enough. [5][6][7] Based on these problems, the study innovatively proposes a deep learning toddler dance generation model based on music rhythm and beat to extract music and dance features respectively. The research aims to generate smooth dances through a generator module, and improve the matching degree between the dance and music generated by the model through a discriminator, enhancing the adaptability of music and dance in terms of rhythm and beat, generating children's dance movements that are harmonious with music and dance, and providing data resource support for children to learn dance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A deep learning model of dance generation for young children based on music rhythm and beat

Kong

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryWith the development of technology, research related to music‐based dance generation models has been increasing. Some of the studies have applied algorithms to dance generation models, but these algorithms suffer from problems such as the inability to make an exact match between music and dance. To solve these problems, the research innovatively proposes a deep learning toddler dance generation model based on music rhythm and beat to extract music and dance features respectively. In addition, the study generates smooth dances through a generator module, improves the match between the dances and music generated by the model through a discriminator, and enhances the representativeness of audio features through a self‐encoder module. Finally, the study completes the validation of the model by comparing the loss functions and other aspects. Results demonstrate that this model has the smallest loss value of 17.58, and that the model generates a better match between dance and music for different music, with values of 8.9, 8, and 7.4. Compared with the comparison model, the study's model for generating dances for young children has better results in terms of dance generation. The study solves the problem that previous algorithms cannot make an exact match between music and dance, and has implications for fields such as cross‐modal generation and games.

show abstract

“…1 The main idea is to introduce attention weights and construct a content vector. The content vector is calculated as shown in Equation (5).…”

Section: Design Of Deep Learning-based Feature Extraction Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A deep learning model of dance generation for young children based on music rhythm and beat

Kong

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…YOLOv3 feature extraction network Darknet-53 includes many 3 × 3 and 1 × 1 convolutional layers, mainly composed of convolution and residual layers. Its complex depth structure is the reason for the slowdown of YOLOv3 training and detection 28 . Five down-sampling times are carried out in the network, and the features are output in the last three layers, and three scales of YOLO layers are generated after processing in the pyramid feature space 29 , 30 .…”

Section: Improved Yolo Lightweight Model Design For Intelligent Stati...mentioning

confidence: 99%

Hybrid YOLOv3 and ReID intelligent identification statistical model for people flow in public places

Zheng

2024

Sci Rep

View full text Add to dashboard Cite

The statistical model for automatic flow recognition is significant for public place management. However, the current model suffers from insufficient statistical accuracy and low lightweight. Therefore, in this study, the structure of the lightweight object detection model "You Only Live Once v3" is optimized, and the "Deep Simple Online Real-Time Tracking" algorithm with the "Person Re-Identification" module is designed, so as to construct a statistical model for people flow recognition. The results showed that the median PersonAP of the designed model was 94.2%, the total detection time was 216 ms, the Rank-1 and Rank-10 were 87.2% and 98.6%, respectively, and the maximum occupied memory of the whole test set was 2.57 MB, which was better than all comparison models. The results indicate that the intelligent identification statistical model for public crowd flow obtained through this design and training has higher statistical accuracy, less computational resource consumption, and faster computing speed. This has certain application space in the management and guidance of crowd flow in public places.

show abstract

“…Although there are many channels in the CL at each scale, it may not cause dimensionality issues when used in cascading. However, after parallel use and fusion, the channels in the MSFF layer increase sharply, which may cause dimensional disasters and limit the network size [23]. Therefore, before entering the next multi-feature fusion module, the MSFF layer is dimensionally reduced to reduce the channels and facilitate feature fusion into the next module.…”

Section: Concatenation Layermentioning

confidence: 99%