2019 6th International Conference on Systems and Informatics (ICSAI) 2019
DOI: 10.1109/icsai48974.2019.9010432
|View full text |Cite
|
Sign up to set email alerts
|

An Lipreading Modle with DenseNet and E3D-LSTM

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 5 publications
0
2
0
Order By: Relevance
“…They have reached an average recognition rate of 35%. Bi et al [40] have developed a DenseNet network structure, the 3D convolution neural network with LSTM (E3DLSTM), which handles the time modeling for features extraction. The CTC layer is then utilized as a cascading time classification.…”
Section: Deep Learning Features Based Modelsmentioning
confidence: 99%
“…They have reached an average recognition rate of 35%. Bi et al [40] have developed a DenseNet network structure, the 3D convolution neural network with LSTM (E3DLSTM), which handles the time modeling for features extraction. The CTC layer is then utilized as a cascading time classification.…”
Section: Deep Learning Features Based Modelsmentioning
confidence: 99%
“…In this context, it is seen that hybrid models give more successful results. In challenging datasets such as the LRW1000 dataset, it is seen to be low in hybrid models (Bi et al 2019, Xiao et al 2020). Real-life data sets are more challenging than other data sets.…”
Section: Figure 4 Usage Rates Of Multiple Datasetsmentioning
confidence: 99%