Fig 1.
The architecture of the proposed DTLME model for feature engineering.
Fig 2.
Generic VGG16 model.
Fig 3.
Pre-trained VGG16 model used for transfer learning.
Fig 4.
Multimodal embedding for feature learning.
(a) User feature learning; (b) Item feature learning.
Fig 5.
Sparse rating matrix for item pi for user ui.
Fig 6.
User-item affinity matrix.
Fig 7.
User profile, similarity calculation and top-n recommendation.
Table 1.
Training and testing set for Brazilian E-Commerce dataset.
Table 2.
Training and testing set for E-Commerce product images dataset.
Fig 8.
Accuracy measures for VGG-16 model.
Fig 9.
Loss for VGG-16 model.
Fig 10.
The average rating for products in BE-dataset.
Fig 11.
MAE for BE-dataset @100 epochs.
Fig 12.
MAE for BE-dataset @20 epochs.
Fig 13.
Precision, recall and F-1 measures for DTLME model.
Table 3.
Performance comparison of proposed model with baseline recommendation techniques.
Fig 14.
Comparative analysis of DTLME model with CSSVD, BPR and TF baseline RSs.
Table 4.
Comparison of the proposed model with baseline algorithms for RMSE on the basis of SR.
Table 5.
Performance comparison for item cold-start problem on BE-dataset.
Table 6.
Performance comparison for user cold-start problem on BE-dataset.