Search alternatives:
codon optimization » wolf optimization (Expand Search)
art optimization » swarm optimization (Expand Search), after optimization (Expand Search), path optimization (Expand Search)
binary base » binary mask (Expand Search), ciliary base (Expand Search), binary image (Expand Search)
phase art » phase a (Expand Search), phase arrest (Expand Search)
codon optimization » wolf optimization (Expand Search)
art optimization » swarm optimization (Expand Search), after optimization (Expand Search), path optimization (Expand Search)
binary base » binary mask (Expand Search), ciliary base (Expand Search), binary image (Expand Search)
phase art » phase a (Expand Search), phase arrest (Expand Search)
-
1
-
2
Proposed architecture testing phase.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
3
Comparison with existing SOTA techniques.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
4
Proposed inverted residual parallel block.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
5
Inverted residual bottleneck block.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
6
Sample classes from the HMDB51 dataset.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
7
Sample classes from UCF101 dataset [40].
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
8
Self-attention module for the features learning.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”
-
9
Residual behavior.
Published 2025“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”