Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation.
Gabriel de Souza Pereira MoreiraSara RabhiRonay AkMd Yasin KabirEven OldridgePublished in: CoRR (2021)
Keyphrases
- multi modal
- multi modality
- fusing multiple
- audio visual
- multiple modalities
- single modality
- image features
- feature set
- collaborative filtering
- low level
- high dimensional
- feature extraction
- context aware
- feature vectors
- image annotation
- contextual information
- spatial context
- auto annotation
- video search
- low contrast
- semantic concepts
- humanoid robot
- multimedia
- co occurrence
- face recognition